© 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. 3624
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    part of a function call or definition (negative activations)

    python-code · gemini-2.5-flash-lite

    assignment to a variable

    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
    -0.03
     Di
    -0.02
    di
    -0.02
    (di
    -0.01
    [
    -0.01
    _di
    -0.01
     di
    -0.01
     me
    -0.01
        ↵
    -0.01
    ()
    -0.01
    POSITIVE LOGITS
    .he
    0.02
     found
    0.02
     P
    0.01
    P
    0.01
    .keys
    0.01
    ],
    0.01
     c
    0.01
    _c
    0.01
    over
    0.01
    cle
    0.01
    Activations Density 90.359%

    No Known Activations