© 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. 6658
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    comma followed by space or new line (negative activations)

    python-code · gemini-2.5-flash-lite

    `and` keyword or string literal

    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
    timal
    -0.02
    losest
    -0.02
    ffe
    -0.02
     optimal
    -0.02
     best
    -0.02
     minimum
    -0.02
     closest
    -0.02
    update
    -0.02
    gest
    -0.02
    arest
    -0.02
    POSITIVE LOGITS
    ise
    0.02
    .pop
    0.02
     other
    0.02
    100
    0.02
    10
    0.01
    50
    0.01
    80
    0.01
    200
    0.01
    70
    0.01
    90
    0.01
    Activations Density 97.974%

    No Known Activations