© 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. 7856
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    argument list separator (negative activations)

    python-code · gemini-2.5-flash-lite

    .grid assignment or arguments

    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
    xF
    -0.02
    a
    -0.02
     queue
    -0.02
    loat
    -0.01
    self
    -0.01
    .random
    -0.01
    _neighbor
    -0.01
    ward
    -0.01
    si
    -0.01
    O
    -0.01
    POSITIVE LOGITS
    rid
    0.03
    ar
    0.02
     w
    0.02
    f
    0.02
    R
    0.01
    d
    0.01
    re
    0.01
     values
    0.01
     code
    0.01
     can
    0.00
    Activations Density 94.352%

    No Known Activations