© 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. 7172
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    tuple unpacking after comma

    python-code · gemini-2.5-flash-lite

    part of a word ending in 'al' (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
    direction
    -0.05
     has
    -0.05
    List
    -0.05
    !
    -0.05
    ('
    -0.05
    an
    -0.04
    turn
    -0.04
    mmand
    -0.04
    ['
    -0.04
    ("
    -0.04
    POSITIVE LOGITS
    ry
    0.13
     {↵
    0.09
     [↵
    0.08
     population
    0.06
     {'
    0.06
    [start
    0.06
     {"
    0.06
    opulation
    0.06
    dividual
    0.06
    endoftext
    0.05
    Activations Density 100.000%

    No Known Activations