© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 5870
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    assignment of a variable

    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
    -0.10
    alculate
    -0.09
    alc
    -0.09
     calculate
    -0.08
    valu
    -0.06
    ran
    -0.05
     ran
    -0.05
    _scores
    -0.05
    .parent
    -0.04
    .ran
    -0.04
    POSITIVE LOGITS
    _index
    0.06
    .ch
    0.05
    .name
    0.04
    .id
    0.04
     //
    0.04
     index
    0.04
    _idx
    0.03
     None
    0.03
    dex
    0.03
    .pop
    0.03
    Activations Density 36.037%

    No Known Activations