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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 6-MLP
    11. 6308
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    function parenthesis and argument separator (negative activations)

    python-code · gemini-2.5-flash-lite

    `'` string literal or method argument

    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
     given
    -0.04
    zero
    -0.03
     spe
    -0.03
    raw
    -0.03
    .add
    -0.03
    visited
    -0.03
    os
    -0.02
     visited
    -0.02
    isited
    -0.02
     return
    -0.02
    POSITIVE LOGITS
    mport
    0.04
     import
    0.03
    .heapp
    0.03
     found
    0.03
     function
    0.03
     I
    0.03
    place
    0.03
     {↵
    0.02
    dule
    0.02
    import
    0.02
    Activations Density 97.364%

    No Known Activations