© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 6-MLP
    11. 7005
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    assignment or comparison (negative activations)

    python-code · gemini-2.5-flash-lite

    method call argument `o`

    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
    (G
    -0.04
    (matrix
    -0.04
    (grid
    -0.04
    (maze
    -0.03
    (graph
    -0.03
    (board
    -0.03
    (data
    -0.02
     :
    -0.02
     ->
    -0.02
    (list
    -0.02
    POSITIVE LOGITS
    >
    0.03
     while
    0.03
    ="
    0.02
    tices
    0.02
     iter
    0.02
    ='
    0.02
    <
    0.02
    times
    0.02
     _
    0.01
    neighbor
    0.01
    Activations Density 57.704%

    No Known Activations