© 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. 5654
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    for loop structure (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
    raph
    -0.11
    .edges
    -0.10
    graph
    -0.09
    edges
    -0.09
     edges
    -0.09
     edge
    -0.09
     Graph
    -0.09
     graph
    -0.09
    _edges
    -0.09
    (graph
    -0.08
    POSITIVE LOGITS
     **
    0.14
    44
    0.11
    40
    0.11
    43
    0.10
    45
    0.10
    42
    0.10
    41
    0.10
    48
    0.10
    46
    0.09
    4
    0.09
    Activations Density 64.281%

    No Known Activations