© 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. 2787
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    list elements separated by commas (negative activations)

    python-code · gemini-2.5-flash-lite

    method name followed by underscore

    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
    _data
    -0.03
    atus
    -0.03
    tail
    -0.03
    ata
    -0.03
    _valid
    -0.02
    fo
    -0.02
     data
    -0.02
    data
    -0.02
     valid
    -0.02
    inf
    -0.02
    POSITIVE LOGITS
     found
    0.05
    over
    0.03
    _rate
    0.03
     set
    0.02
    _move
    0.02
    _li
    0.02
    ven
    0.02
    utation
    0.02
    apac
    0.01
    op
    0.01
    Activations Density 84.696%

    No Known Activations