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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 2-MLP
    11. 4789
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    assignment to variable 'a' (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
     {↵
    -0.12
     {'
    -0.12
     {"
    -0.11
    ↵        ↵
    -0.05
    quen
    -0.04
            ↵
    -0.04
    lt
    -0.03
     [↵
    -0.03
    L
    -0.03
     calculate
    -0.02
    POSITIVE LOGITS
    !
    0.07
    s
    0.03
    ↵    ↵
    0.03
     range
    0.03
    old
    0.03
    .co
    0.02
    args
    0.01
    .c
    0.01
    iti
    0.00
    sign
    0.00
    Activations Density 9.621%

    No Known Activations