© 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. 683
    Prev
    Next
    INDEX
    Explanations

    prime check or is_integer (negative activations)

    python-code · gemini-2.5-flash-lite

    import unittest

    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
    ner
    -0.16
    _distance
    -0.15
    _route
    -0.14
    _edge
    -0.11
    one
    -0.09
     of
    -0.08
    _b
    -0.07
    all
    -0.07
    y
    -0.06
    B
    -0.05
    POSITIVE LOGITS
    ilen
    0.36
    List
    0.21
    _ids
    0.21
    apac
    0.18
    _info
    0.14
    _weight
    0.12
     n
    0.11
    _n
    0.11
    _dict
    0.11
     data
    0.10
    Activations Density 97.611%

    No Known Activations