© 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. 6-MLP
    11. 5467
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    comma followed by g in method arguments (negative activations)

    python-code · gemini-2.5-flash-lite

    assignment after loop 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
    .add
    -0.06
    .append
    -0.05
     -=
    -0.05
    .remove
    -0.04
     +=
    -0.04
     ==
    -0.03
    _sum
    -0.03
     If
    -0.03
    .write
    -0.03
     sum
    -0.03
    POSITIVE LOGITS
    timal
    0.10
    losest
    0.10
     optimal
    0.08
     best
    0.08
     closest
    0.07
    gest
    0.07
    arest
    0.07
     shortest
    0.07
    hortest
    0.06
    verage
    0.06
    Activations Density 48.504%

    No Known Activations