© 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. 2-MLP
    11. 7867
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    tuple assignment comma (negative activations)

    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
     dx
    -0.08
     enumerate
    -0.08
     ac
    -0.07
    [x
    -0.06
    (x
    -0.06
     Calculate
    -0.06
     S
    -0.06
     Graph
    -0.06
    div
    -0.06
     Par
    -0.06
    POSITIVE LOGITS
    ↵↵
    0.16
    ↵        ↵
    0.15
    ↵            ↵
    0.15
    ↵    ↵
    0.14
    ↵↵↵
    0.12
    <|
    0.12
    |>
    0.12
    ↵
    0.10
    "↵↵
    0.09
    č
    0.09
    Activations Density 83.594%

    No Known Activations