© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 4956
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    `import` or `def` followed by identifier

    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
    mo
    -0.22
    la
    -0.10
    lat
    -0.06
    uzz
    -0.06
    xb
    -0.04
    xa
    -0.04
    id
    -0.04
    uzzle
    -0.03
    old
    -0.03
    ac
    -0.02
    POSITIVE LOGITS
    T
    0.13
    fs
    0.08
    f
    0.07
    ¤
    0.07
    16
    0.07
    fe
    0.07
    ft
    0.06
    fi
    0.06
     final
    0.05
     t
    0.05
    Activations Density 6.172%

    No Known Activations