© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 4778
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    function argument (negative activations)

    python-code · gemini-2.5-flash-lite

    left side of tkinter widget

    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
    blem
    -0.04
    ctionary
    -0.04
    dividual
    -0.04
    fig
    -0.04
    dices
    -0.03
    maining
    -0.03
    stance
    -0.03
    vent
    -0.03
    duct
    -0.03
    splay
    -0.03
    POSITIVE LOGITS
    60
    0.06
    uristic
    0.05
    46
    0.03
    _h
    0.03
     h
    0.03
    vel
    0.02
    lat
    0.02
    itude
    0.02
     lat
    0.02
    dge
    0.02
    Activations Density 33.277%

    No Known Activations