© 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. 6197
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    import module as alias

    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
    -0.05
     [[
    -0.02
     tuple
    -0.02
     ("
    -0.01
    \n
    -0.01
    -0.01
     [(
    -0.01
    c
    -0.01
    em
    -0.00
    '
    0.00
    POSITIVE LOGITS
    verage
    0.06
    v
    0.05
    id
    0.05
     visited
    0.05
    of
    0.04
    r
    0.03
    l
    0.03
    vent
    0.03
    visited
    0.03
    ^
    0.03
    Activations Density 1.564%

    No Known Activations