© 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. 7148
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    tuple unpacking comma (negative activations)

    python-code · gemini-2.5-flash-lite

    key=lambda x: x[1]

    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
     total
    -0.02
    No
    -0.01
    ner
    -0.01
    "{
    -0.01
     n
    -0.01
    .n
    -0.01
     dp
    -0.01
     nx
    -0.01
    (N
    -0.01
    num
    -0.01
    POSITIVE LOGITS
    uple
    0.02
    (map
    0.02
    ↵
    0.02
     map
    0.02
     len
    0.02
    ._
    0.01
    list
    0.01
    ener
    0.01
     range
    0.01
     list
    0.01
    Activations Density 57.291%

    No Known Activations