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

    Neuronpedia

    INDEX
    Explanations

    legal opinions

    np_max-act · gemini-2.0-flash

    This neuron detects the header lines of legal case citations (the party names, reporter volume and page, court name, and date that appear at the top of opinions).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    "&
    -0.06
     pans
    -0.05
    .swt
    -0.05
    بد
    -0.05
     متحده
    -0.05
    loadModel
    -0.05
    .hasMore
    -0.05
    těl
    -0.05
     everlasting
    -0.05
    .sys
    -0.05
    POSITIVE LOGITS
    aturated
    0.07
     बस
    0.07
    oldur
    0.07
     Вар
    0.06
     interv
    0.06
     Ciudad
    0.06
     çocuğ
    0.06
    pare
    0.06
     rahatsız
    0.06
    стан
    0.06
    Act Density 0.011%

    No Known Activations