© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 6-MLP
    11. 2006
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    global keyword

    python-code · gemini-2.5-flash-lite

    exponentiation operator '**' (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
     If
    -0.05
     "
    -0.03
     if
    -0.03
    .append
    -0.03
     <=
    -0.02
    rue
    -0.02
     -=
    -0.02
    -0.02
    .remove
    -0.02
    ound
    -0.02
    POSITIVE LOGITS
     dp
    0.05
    _queue
    0.04
    rontier
    0.04
     heap
    0.03
    queue
    0.03
     collections
    0.03
    isit
    0.03
     queue
    0.03
    ache
    0.02
     deque
    0.02
    Activations Density 99.615%

    No Known Activations