© 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. 2852
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    attribute access, list indexing (negative activations)

    python-code · gemini-2.5-flash-lite

    .split method call

    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
    input
    -0.05
     input
    -0.04
    _input
    -0.04
    ...
    -0.04
    (input
    -0.03
    .txt
    -0.03
    ample
    -0.03
    structions
    -0.03
    En
    -0.02
     run
    -0.02
    POSITIVE LOGITS
    loat
    0.10
    (int
    0.09
    [int
    0.08
    int
    0.08
     int
    0.08
     float
    0.07
    (map
    0.05
     bo
    0.04
     match
    0.04
    (list
    0.04
    Activations Density 99.996%

    No Known Activations