© 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. 2812
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    string formatting and joining (negative activations)

    python-code · gemini-2.5-flash-lite

    .get, split, or insert method calls

    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
     function
    -0.06
    mport
    -0.04
    ",↵
    -0.03
    thod
    -0.03
     algorithm
    -0.03
     <=
    -0.03
    ',↵
    -0.03
     import
    -0.03
     ",
    -0.03
    :",
    -0.03
    POSITIVE LOGITS
     all
    0.04
    input
    0.04
    all
    0.04
    .position
    0.04
    distances
    0.03
     input
    0.03
     positions
    0.03
    urrent
    0.03
    jac
    0.03
    _distances
    0.03
    Activations Density 99.276%

    No Known Activations