© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 6-MLP
    11. 3358
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    method call argument list (negative activations)

    python-code · gemini-2.5-flash-lite

    function definition keyword

    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
    .index
    -0.06
    <
    -0.04
     <=
    -0.03
    type
    -0.03
     <
    -0.03
    class
    -0.02
    atus
    -0.02
     dfs
    -0.02
     print
    -0.02
     self
    -0.02
    POSITIVE LOGITS
    .n
    0.03
     rows
    0.03
     n
    0.03
     cols
    0.03
    26
    0.02
    vertices
    0.02
     >
    0.02
    blem
    0.02
     import
    0.02
    (n
    0.02
    Activations Density 99.945%

    No Known Activations