© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 6-MLP
    11. 3046
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    exponentiation operator (negative activations)

    python-code · gemini-2.5-flash-lite

    argument assignment with comma separation

    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
    rontier
    -0.07
     visited
    -0.06
    _queue
    -0.06
    queue
    -0.06
    visited
    -0.05
     heap
    -0.05
     next
    -0.05
     queue
    -0.04
     collections
    -0.04
    _edges
    -0.04
    POSITIVE LOGITS
    _grid
    0.06
    structions
    0.04
     grid
    0.04
    adj
    0.04
    K
    0.03
    grid
    0.03
    A
    0.03
    _key
    0.03
     k
    0.02
    k
    0.02
    Activations Density 99.769%

    No Known Activations