© 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. 6489
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    list indexing and slicing (negative activations)

    python-code · gemini-2.5-flash-lite

    opening parenthesis in function 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
     and
    -0.03
     \
    -0.02
    ow
    -0.02
     two
    -0.02
     Calculate
    -0.02
    alculate
    -0.01
    alc
    -0.01
     ver
    -0.01
     +
    -0.01
    ,
    -0.01
    POSITIVE LOGITS
     [↵
    0.04
    rack
    0.04
    .values
    0.04
     [(
    0.04
     deque
    0.03
     collections
    0.03
     enumerate
    0.03
    reshold
    0.03
    .keys
    0.03
     ['
    0.03
    Activations Density 96.488%

    No Known Activations