© 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. 2203
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    for loop construct (negative activations)

    python-code · gemini-2.5-flash-lite

    function arguments separator

    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
    .append
    -0.02
     -=
    -0.02
    .remove
    -0.02
    .add
    -0.02
     +=
    -0.02
    :↵
    -0.01
     If
    -0.01
    .write
    -0.01
     the
    -0.01
    ':
    -0.01
    POSITIVE LOGITS
     Returns
    0.05
     Output
    0.03
     Return
    0.03
    re
    0.03
     self
    0.02
    instance
    0.02
    (self
    0.02
    <
    0.02
     Find
    0.02
     <=
    0.02
    Activations Density 90.088%

    No Known Activations