© 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. 6906
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    range start with len (negative activations)

    python-code · gemini-2.5-flash-lite

    assignment after conditional check

    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
     Calculate
    -0.03
     calculate
    -0.03
    alculate
    -0.03
    alc
    -0.03
     while
    -0.03
    .pop
    -0.02
     float
    -0.02
    uel
    -0.02
    valu
    -0.02
     iter
    -0.02
    POSITIVE LOGITS
    .parent
    0.03
     //
    0.03
     !=
    0.02
     parent
    0.02
     Ex
    0.02
    .ch
    0.01
     /
    0.01
     prev
    0.01
    atus
    0.01
    .random
    0.01
    Activations Density 67.334%

    No Known Activations