© 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. 3375
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    variable assignment or print call (negative activations)

    python-code · gemini-2.5-flash-lite

    variable name parts followed by specific tokens

    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
    ¾
    -0.03
    15
    -0.02
    form
    -0.02
    Ń
    -0.02
    01
    -0.01
    ord
    -0.01
    's
    -0.01
    split
    -0.01
    25
    -0.01
    is
    -0.01
    POSITIVE LOGITS
    isited
    0.06
    orted
    0.03
    maining
    0.03
    visited
    0.03
    quired
    0.03
    use
    0.03
    ted
    0.03
    red
    0.03
    ded
    0.03
    ef
    0.02
    Activations Density 90.894%

    No Known Activations