© 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. 4957
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    assignment to variables (negative activations)

    python-code · gemini-2.5-flash-lite

    self attribute name prefix

    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
     all
    -0.04
    all
    -0.04
    (len
    -0.04
     any
    -0.03
     by
    -0.02
    _by
    -0.02
    .keys
    -0.02
    ly
    -0.02
     each
    -0.02
    ree
    -0.01
    POSITIVE LOGITS
     found
    0.02
    0.01
     set
    0.01
    No
    0.01
    ner
    0.01
     n
    0.01
    .n
    0.01
     nx
    0.01
    lace
    0.01
    (N
    0.01
    Activations Density 79.992%

    No Known Activations