© 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. 2-MLP
    11. 6125
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    variable assignment or list definition (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
     Ex
    -0.09
     exp
    -0.05
    `
    -0.05
    e
    -0.04
    erson
    -0.04
    ec
    -0.03
    _n
    -0.03
    da
    -0.02
    fe
    -0.02
    ef
    -0.02
    POSITIVE LOGITS
     enum
    0.15
    ateg
    0.12
    ¢
    0.12
    en
    0.11
    sen
    0.11
    ren
    0.11
    den
    0.10
    ven
    0.10
    ency
    0.09
    En
    0.09
    Activations Density 80.580%

    No Known Activations