© 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. 7248
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    `str.lower` or string literals (negative activations)

    python-code · gemini-2.5-flash-lite

    less than or less than or equal to

    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
    use
    -0.03
    ke
    -0.03
    '.
    -0.03
    add
    -0.03
    &
    -0.02
     :
    -0.02
    {
    -0.02
    -
    -0.02
     &
    -0.02
    neighbor
    -0.01
    POSITIVE LOGITS
    >
    0.04
    (G
    0.03
    (matrix
    0.03
    (grid
    0.03
    (maze
    0.03
    (graph
    0.03
    .co
    0.03
    (board
    0.02
    ;
    0.02
    (data
    0.02
    Activations Density 91.606%

    No Known Activations