© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 6-MLP
    11. 4504
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    call to super().__init__()

    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
    _with
    -0.09
     tree
    -0.03
     =
    -0.02
     return
    -0.01
     Returns
    -0.01
     Return
    -0.01
    =
    -0.01
    turn
    -0.01
     pi
    -0.01
     ==
    -0.01
    POSITIVE LOGITS
    init
    0.10
    itial
    0.09
    ctor
    0.07
    ().
    0.06
     Initialize
    0.05
     __
    0.04
    __':↵
    0.04
    In
    0.04
    00
    0.04
    __
    0.04
    Activations Density 32.797%

    No Known Activations