© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 6-MLP
    11. 6422
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    class declaration or inheritance

    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
    {
    -0.08
     representing
    -0.07
    '.
    -0.06
     that
    -0.06
     of
    -0.06
     Returns
    -0.05
    <
    -0.05
     given
    -0.04
    of
    -0.04
     whe
    -0.04
    POSITIVE LOGITS
    ('
    0.04
    ameters
    0.04
    ar
    0.03
     ('
    0.03
    ("
    0.03
     ["
    0.03
    ase
    0.03
    al
    0.03
    t
    0.03
     ['
    0.03
    Activations Density 21.838%

    No Known Activations