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

    Neuronpedia

    INDEX
    Explanations

    court filings

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on the header and footer metadata of legal documents—e.g. filing stamps, court names, dates, clerk notations, and docket numbers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ́t
    -0.07
     distilled
    -0.07
    ounc
    -0.06
    ємо
    -0.06
    ’є
    -0.06
     tox
    -0.06
    oğ
    -0.06
    requete
    -0.06
     DVDs
    -0.06
     poured
    -0.06
    POSITIVE LOGITS
     clinic
    0.07
     understanding
    0.07
    押
    0.07
    947
    0.07
    χεί
    0.07
     clinics
    0.07
    (Void
    0.06
     пок
    0.06
    观看
    0.06
     меди
    0.06
    Act Density 0.003%

    No Known Activations