© 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. 2-MLP
    11. 7539
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    method call parenthesis

    python-code · gemini-2.5-flash-lite

    list assignment (negative activations)

    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
    ax
    -0.04
    py
    -0.04
    µ
    -0.03
    _max
    -0.03
    (max
    -0.02
    °
    -0.02
    max
    -0.02
    44
    -0.02
     max
    -0.02
     char
    -0.02
    POSITIVE LOGITS
    _start
    0.06
     start
    0.05
    _left
    0.05
     left
    0.05
     source
    0.05
    start
    0.05
    .start
    0.05
    irst
    0.05
    left
    0.04
     low
    0.04
    Activations Density 100.000%

    No Known Activations