© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 2-MLP
    11. 4126
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    list comprehension or generator expression

    python-code · gemini-2.5-flash-lite

    function definition or import statement (negative activations)

    python-code · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 256 tokens each
    Dataset (Dashboard)
    neuronpedia/python-code-simplified
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __":↵
    -0.13
    __':↵
    -0.11
    __(
    -0.10
    ()<|
    -0.10
    __
    -0.10
     "__
    -0.10
     break
    -0.08
     '__
    -0.07
    )<|
    -0.07
    main
    -0.07
    POSITIVE LOGITS
     in
    0.07
    .m
    0.06
    ry
    0.06
                    ↵
    0.05
    .↵↵
    0.05
    lit
    0.05
     adj
    0.05
    adj
    0.05
    split
    0.04
    reshold
    0.04
    Activations Density 96.161%

    No Known Activations