© 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. 6-MLP
    11. 3371
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    random choice string generation (negative activations)

    python-code · gemini-2.5-flash-lite

    print statement or target argument

    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
    ...
    -0.01
    =True
    -0.01
     other
    -0.01
    ["
    -0.01
    tity
    -0.01
     is
    -0.01
    ['
    -0.01
     as
    -0.01
    .items
    -0.01
    tail
    -0.00
    POSITIVE LOGITS
     +
    0.04
    +
    0.02
     None
    0.02
     +=
    0.02
    None
    0.02
     and
    0.02
     two
    0.02
    [(
    0.01
    ][
    0.01
     main
    0.01
    Activations Density 64.131%

    No Known Activations