© 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. 6-MLP
    11. 4437
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    comma followed by argument

    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
    arent
    -0.10
     parent
    -0.07
    ool
    -0.05
    ory
    -0.05
    age
    -0.05
    hest
    -0.05
    un
    -0.04
    rent
    -0.04
    ren
    -0.04
    Ö
    -0.04
    POSITIVE LOGITS
    .position
    0.09
    osition
    0.08
    ill
    0.07
    on
    0.06
    ).
    0.06
     with
    0.06
     pos
    0.05
    as
    0.05
    ty
    0.05
    os
    0.05
    Activations Density 2.585%

    No Known Activations