© 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. Residual Stream
    9. 7-RESID
    11. 1214
    Prev
    Next
    INDEX
    Explanations

    string literal or argument to encode (negative activations)

    python-code · gemini-2.5-flash-lite

    import statements from datetime

    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
    .x
    -0.25
    _x
    -0.24
     x
    -0.21
    lat
    -0.21
     lat
    -0.21
    X
    -0.20
    x
    -0.17
     dx
    -0.16
     row
    -0.13
    row
    -0.13
    POSITIVE LOGITS
    **
    0.09
    .in
    0.07
    _con
    0.06
    _re
    0.06
    vi
    0.05
    con
    0.05
    K
    0.05
     initial
    0.03
    '
    0.00
    #
    0.00
    Activations Density 100.000%

    No Known Activations