Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash

    the neuron detects tokens that are part of legal statute or code citations—e.g. section symbols (§), statute numbers, and parenthesized subsection labels.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    __.__
    -0.07
    Lower
    -0.06
     metod
    -0.06
    лем
    -0.06
     cozy
    -0.06
     owl
    -0.06
    िछ
    -0.06
    bose
    -0.06
    Class
    -0.06
    CustomerId
    -0.05
    POSITIVE LOGITS
     legis
    0.07
    Fallback
    0.07
     zač
    0.07
     acknow
    0.06
    _Selected
    0.06
    ียก
    0.06
     Repos
    0.06
     drive
    0.06
    >About
    0.06
     prosecutors
    0.06
    Act Density 0.009%

    No Known Activations