© 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. 6902
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    math module method calls

    python-code · gemini-2.5-flash-lite

    logical OR conditional `or` (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
     coordinates
    -0.07
     positions
    -0.06
     Testing
    -0.05
    ess
    -0.04
    alc
    -0.04
     ->
    -0.04
     Test
    -0.04
    test
    -0.04
    alculate
    -0.04
     test
    -0.04
    POSITIVE LOGITS
    _c
    0.06
    ize
    0.04
    stru
    0.04
    ilities
    0.04
    ))
    0.03
    é
    0.03
    iz
    0.03
    æ
    0.03
    å
    0.03
    è
    0.03
    Activations Density 100.000%

    No Known Activations