© 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. 7693
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    list element access (negative activations)

    python-code · gemini-2.5-flash-lite

    static method decorator or numpy.linalg

    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
     '
    -0.02
     "
    -0.02
    .txt
    -0.01
    .position
    -0.01
    ls
    -0.01
    _co
    -0.01
    co
    -0.01
     column
    -0.01
    _coords
    -0.01
    _position
    -0.01
    POSITIVE LOGITS
     found
    0.02
    .is
    0.02
    .keys
    0.01
     heapq
    0.01
    ools
    0.01
    .num
    0.01
     math
    0.01
    [row
    0.01
     file
    0.01
     us
    0.01
    Activations Density 95.806%

    No Known Activations