© 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. 4568
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    negative numbers

    python-code · gemini-2.5-flash-lite

    comparison operators and assignment (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
     as
    -0.07
     at
    -0.06
    Ĥ
    -0.05
    as
    -0.04
    Ĺ
    -0.04
    unction
    -0.04
     ac
    -0.03
    unc
    -0.03
    ÷
    -0.03
    Á
    -0.03
    POSITIVE LOGITS
    <
    0.03
    ed
    0.03
    \
    0.03
     part
    0.03
    ;
    0.03
    ood
    0.03
    >
    0.03
     ((
    0.03
    _part
    0.03
    mple
    0.03
    Activations Density 100.000%

    No Known Activations