© 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. 6924
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    `sum` or `random` keywords (negative activations)

    python-code · gemini-2.5-flash-lite

    variable assignment after range

    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
    fset
    -0.02
    ","
    -0.02
    inal
    -0.02
     possible
    -0.02
    hor
    -0.02
     directions
    -0.02
    ep
    -0.02
    result
    -0.02
     [(
    -0.01
     neighbors
    -0.01
    POSITIVE LOGITS
     Tuple
    0.02
    =True
    0.02
    ()
    0.02
     form
    0.02
    tity
    0.01
    rc
    0.01
     If
    0.01
    tail
    0.01
    ype
    0.01
    type
    0.01
    Activations Density 85.889%

    No Known Activations