© 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. 7081
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    opening parenthesis followed by string literal

    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
     >
    -0.06
     or
    -0.04
    _set
    -0.03
    che
    -0.03
    put
    -0.03
     /
    -0.02
    '
    -0.02
    _map
    -0.02
    .random
    -0.02
    gest
    -0.02
    POSITIVE LOGITS
    |>
    0.08
    lit
    0.08
    1
    0.06
    07
    0.05
    01
    0.05
    03
    0.05
    weight
    0.05
    00
    0.05
    ut
    0.05
    02
    0.05
    Activations Density 62.757%

    No Known Activations