© 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. 1748
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    attribute assignment or method call

    python-code · gemini-2.5-flash-lite

    print function calls and if __name__ (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
    ble
    -0.06
    e
    -0.06
    ors
    -0.05
    es
    -0.04
    ed
    -0.03
    s
    -0.03
    (row
    -0.02
    ay
    -0.02
    ·
    -0.02
    E
    -0.02
    POSITIVE LOGITS
    op
    0.06
    on
    0.05
    oc
    0.04
    ram
    0.04
    un
    0.04
    os
    0.03
    o
    0.03
    als
    0.03
    ample
    0.03
    he
    0.03
    Activations Density 84.364%

    No Known Activations