© 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. 6401
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    random.choice and .islower (negative activations)

    python-code · gemini-2.5-flash-lite

    fetch one or all

    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
    h
    -0.04
     not
    -0.03
    No
    -0.03
    -0.02
    ad
    -0.02
     !=
    -0.02
    Error
    -0.02
    ver
    -0.02
     dist
    -0.02
     distances
    -0.02
    POSITIVE LOGITS
    ch
    0.03
    >
    0.02
    ow
    0.01
    is
    0.01
    ist
    0.01
    <extra_output_id:2047>
    0.01
    .
    0.01
    me
    0.01
     L
    0.01
    s
    0.00
    Activations Density 17.562%

    No Known Activations