© 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. 7386
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    `random` module usage (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
    3
    -0.14
    2
    -0.14
    4
    -0.13
    1
    -0.13
    6
    -0.11
    5
    -0.10
    7
    -0.10
    mmon
    -0.09
    8
    -0.09
    9
    -0.09
    POSITIVE LOGITS
     as
    0.04
     at
    0.03
     """
    0.03
     """↵
    0.03
     ac
    0.02
    as
    0.02
    \
    0.01
     Example
    0.01
     '
    0.01
    (current
    0.01
    Activations Density 74.699%

    No Known Activations