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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 2-MLP
    11. 4953
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    function argument parentheses (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
    direction
    -0.08
    uild
    -0.08
     moves
    -0.07
    turn
    -0.07
    mmand
    -0.07
     build
    -0.07
    uil
    -0.07
     move
    -0.07
    _move
    -0.07
     direction
    -0.06
    POSITIVE LOGITS
    +
    0.05
    -
    0.05
    ong
    0.05
    {
    0.04
    code
    0.04
    *
    0.04
    s
    0.03
    #
    0.03
    %
    0.03
    out
    0.03
    Activations Density 99.446%

    No Known Activations