© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 6-MLP
    11. 2161
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    closing parenthesis or set keyword (negative activations)

    python-code · gemini-2.5-flash-lite

    __main__ guard

    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
    ('
    -0.03
    ("
    -0.03
    _of
    -0.03
    (f
    -0.02
    -
    -0.02
    (N
    -0.02
    (min
    -0.02
    (max
    -0.02
    (maze
    -0.02
     -
    -0.02
    POSITIVE LOGITS
    str
    0.02
    _str
    0.02
    _string
    0.01
    int
    0.01
    f
    0.01
     from
    0.01
    ch
    0.01
    _list
    0.01
    raw
    0.01
     target
    0.00
    Activations Density 49.807%

    No Known Activations