© 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
    2. OpenAI · Weight-Sparse Transformers
    3. CircuitGPT-Python
    4. MLP
    5. 6-MLP
    6. 3612
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    one or two angle brackets

    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
     ".
    -0.05
     '.
    -0.05
     import
    -0.03
    '.
    -0.03
     '#
    -0.03
    ied
    -0.03
    ude
    -0.03
     :
    -0.02
    endencies
    -0.02
    red
    -0.02
    POSITIVE LOGITS
    <
    0.13
    >
    0.10
    )],↵
    0.07
     represe
    0.07
    ]),
    0.07
    ))<|
    0.07
    )):↵
    0.07
    ])↵↵
    0.07
    )]↵↵
    0.06
    ]):↵
    0.06
    Activations Density 21.208%

    No Known Activations