© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 6-MLP
    11. 1735
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    handler or argument start

    python-code · gemini-2.5-flash-lite

    function call arguments (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
    Negative Logits
    get
    -0.04
    kets
    -0.03
    ket
    -0.03
     Calculate
    -0.02
    ain
    -0.02
    end
    -0.02
    ho
    -0.02
    ow
    -0.02
    set
    -0.02
    etween
    -0.02
    POSITIVE LOGITS
    uristic
    0.04
    60
    0.04
    ro
    0.03
    46
    0.02
    ag
    0.02
    hild
    0.02
    99
    0.02
    _neighbor
    0.02
     new
    0.01
    55
    0.01
    Activations Density 78.475%

    No Known Activations