© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 6-MLP
    11. 4188
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    function call or list append (negative activations)

    python-code · gemini-2.5-flash-lite

    variable assignment or parameter

    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
     ele
    -0.04
    .name
    -0.04
    .id
    -0.04
    input
    -0.03
    _idx
    -0.03
    _input
    -0.03
    .txt
    -0.03
    apping
    -0.03
    dex
    -0.03
     input
    -0.03
    POSITIVE LOGITS
    anage
    0.08
    olver
    0.07
     Create
    0.05
    uil
    0.05
    ator
    0.04
     =
    0.04
    tim
    0.04
    .keys
    0.04
     ->
    0.04
    Ö
    0.03
    Activations Density 98.622%

    No Known Activations