© 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. 2-MLP
    11. 7865
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    negative numbers or list indexing

    python-code · gemini-2.5-flash-lite

    closing parenthesis or `print` (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
    List
    -0.03
    _index
    -0.03
    ):
    -0.03
    .
    -0.03
    9
    -0.02
    59
    -0.02
    90
    -0.02
     are
    -0.02
    In
    -0.02
    ())
    -0.02
    POSITIVE LOGITS
     representing
    0.08
     Returns
    0.07
    actions
    0.06
    apping
    0.06
    loor
    0.06
    ariable
    0.06
     model
    0.06
    dint
    0.06
    erge
    0.06
    lif
    0.06
    Activations Density 100.000%

    No Known Activations