© 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. 4064
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    the number 1 in expressions (negative activations)

    python-code · gemini-2.5-flash-lite

    parentheses around calculation

    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
    ]
    -0.04
     {↵
    -0.04
     ("
    -0.04
     (
    -0.04
     (-
    -0.03
     ('
    -0.03
     ((
    -0.03
    [(
    -0.03
     me
    -0.03
    ((
    -0.02
    POSITIVE LOGITS
     [
    0.02
     ==
    0.02
     or
    0.02
    The
    0.02
     *
    0.02
    .randint
    0.02
    +
    0.02
    urrent
    0.02
    .name
    0.02
    .id
    0.02
    Activations Density 80.498%

    No Known Activations