© 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. 2873
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    class method calls (negative activations)

    python-code · gemini-2.5-flash-lite

    inside method definition

    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
    .parent
    -0.02
     _
    -0.02
     parent
    -0.01
    =
    -0.01
     prev
    -0.01
     !=
    -0.01
    ven
    -0.01
    (int
    -0.01
     pre
    -0.01
    ame
    -0.01
    POSITIVE LOGITS
    ","
    0.04
    ",
    0.04
    ',
    0.04
    ")↵
    0.03
     ",
    0.03
    ')↵
    0.02
     dictionary
    0.02
    ctionary
    0.02
    re
    0.02
    uple
    0.02
    Activations Density 40.174%

    No Known Activations