© 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. 2820
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    variable assignment with `a` (negative activations)

    python-code · gemini-2.5-flash-lite

    variable assignment

    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
    for
    -0.06
     for
    -0.06
    alculate
    -0.03
    self
    -0.03
     calculate
    -0.03
     self
    -0.03
    enerate
    -0.03
    isit
    -0.03
    urrent
    -0.03
    olve
    -0.03
    POSITIVE LOGITS
     function
    0.06
     raise
    0.04
     -
    0.03
     Example
    0.03
    None
    0.03
    alse
    0.02
     None
    0.02
    -
    0.02
    0.02
     []↵↵
    0.02
    Activations Density 95.359%

    No Known Activations