© 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. 2071
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    function calls and `__init__` methods (negative activations)

    python-code · gemini-2.5-flash-lite

    self in method parameters

    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
    _i
    -0.04
    alse
    -0.04
    Ã
    -0.04
    rue
    -0.04
    bs
    -0.03
    (v
    -0.03
    False
    -0.03
    fo
    -0.03
    True
    -0.03
     True
    -0.03
    POSITIVE LOGITS
    arehouse
    0.06
    udent
    0.06
    light
    0.06
    uild
    0.05
    stac
    0.05
    liver
    0.05
    rontier
    0.04
    mployee
    0.04
    ruck
    0.04
    ward
    0.04
    Activations Density 99.199%

    No Known Activations