© 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. 7796
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    `_e` followed by common method/attribute name parts

    python-code · gemini-2.5-flash-lite

    list index access `[]` and function calls `()` (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
    _of
    -0.01
    _info
    -0.01
    ¹
    -0.01
     al
    -0.00
    _and
    -0.00
    '
    0.00
    #
    0.00
    &
    0.00
    %
    0.00
    *
    0.00
    POSITIVE LOGITS
    ilities
    0.08
    iz
    0.07
    ize
    0.07
    ise
    0.05
    ized
    0.05
     e
    0.05
    rib
    0.04
    ir
    0.04
    ffic
    0.04
    light
    0.04
    Activations Density 100.000%

    No Known Activations