© 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. 4713
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    string.ascii_letters (negative activations)

    python-code · gemini-2.5-flash-lite

    attribute assignments in __init__

    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
    ake
    -0.01
    isit
    -0.01
    ser
    -0.01
    ain
    -0.01
    im
    -0.01
    ag
    -0.01
    n
    -0.01
    lace
    -0.01
    chedule
    -0.00
    an
    -0.00
    POSITIVE LOGITS
    ry
    0.02
     t
    0.02
    pe
    0.01
    end
    0.01
    se
    0.01
    is
    0.01
    ass
    0.01
    h
    0.00
    essage
    0.00
     all
    0.00
    Activations Density 67.618%

    No Known Activations