Research map / Large language models / Language, safety and interpretability
Convergent Representations of Computer Programs in Human and Artificial Neural Networks
Shashank Srikant, Ben Lipkin, Anna A Ivanova, Evelina Fedorenko, Una-May O'Reilly
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| decode code properties from Multiple Demand (MD) vs Language system brain representations | ridge decoders on fMRI · dynamic analysis (runtime steps) | Pearson correlation | Improved |
| decode static analysis vs dynamic analysis properties from MD | MD system · code properties | decoding score | Improved |
| decode variable language (English vs Japanese names) from MD and LS | MD and Language systems · variable language | classification accuracy | No clear effect |
| add MD or LS to Visual system features in partial regression (ablation) | Visual system decoder · control flow, data type, static and dynamic analysis | decoding accuracy | Improved |
| map brain to code models from MD instead of LS | brain-to-model ridge mapping · CodeBERTa, CodeTransformer, seq2seq, TF-IDF | ranked accuracy | Improved |
| compare code models to Token Projection baseline for MD mapping (ablation) | MD mapping · CodeBERTa, CodeTransformer, bag-of-words | ranked accuracy | Mixed |
| compare code models to Token Projection baseline for Language system mapping (ablation) | LS mapping · all code models | ranked accuracy | No clear effect |
Closest papers by meaning
- Neural Code Comprehension: A Learnable Representation of Code Semantics (NeurIPS 2018 · similarity 0.87)
- Divergences between Language Models and Human Brains (NeurIPS 2024 · similarity 0.86)
- Far from the Shallow: Brain-Predictive Reasoning Embedding through Residual Disentanglement (NeurIPS 2025 · similarity 0.85)
- Hierarchical Frequency Tagging Probe (HFTP): A Unified Approach to Investigate Syntactic Structure Representations in Large Language Models and the Human Brain (NeurIPS 2025 · similarity 0.85)
- fMRI predictors based on language models of increasing complexity recover brain left lateralization (NeurIPS 2024 · similarity 0.84)
- The Semantic Hub Hypothesis: Language Models Share Semantic Representations Across Languages and Modalities (ICLR 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
