© 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. 3151
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    for loop variable

    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
    udoku
    -0.08
    aze
    -0.08
    oard
    -0.07
     maze
    -0.07
    blem
    -0.07
    grid
    -0.07
    _grid
    -0.06
     grid
    -0.06
     graph
    -0.06
    .grid
    -0.06
    POSITIVE LOGITS
     for
    0.09
    (range
    0.09
     any
    0.05
     all
    0.05
    hild
    0.04
    _neighbor
    0.04
     continue
    0.03
    all
    0.03
    (len
    0.03
    hildren
    0.03
    Activations Density 97.780%

    No Known Activations