© 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. 2721
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    list indexing `[]` (negative activations)

    python-code · gemini-2.5-flash-lite

    is instance

    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
     each
    -0.07
    .heapp
    -0.04
    ique
    -0.04
    re
    -0.03
    oard
    -0.03
    aze
    -0.03
    blem
    -0.03
    grid
    -0.03
    _grid
    -0.03
     grid
    -0.03
    POSITIVE LOGITS
    qrt
    0.06
     abs
    0.05
    ab
    0.04
     elif
    0.03
     if
    0.02
     del
    0.02
     distance
    0.02
    les
    0.02
    class
    0.01
     math
    0.01
    Activations Density 45.352%

    No Known Activations