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

    Neuronpedia

    INDEX
    Explanations

    hardware basics and support

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    니다
    2.16
    يني
    1.79
    뭔
    1.77
    1.73
     Dieses
    1.66
    合った
    1.66
    ட்
    1.62
     atvej
    1.62
    ের
    1.60
     नती
    1.57
    POSITIVE LOGITS
    ৮
    2.05
    ни
    2.03
     trebui
    1.98
    <0x80>
    1.84
    boiled
    1.84
    as
    1.71
    شناسی
    1.66
    eurs
    1.63
    ੀ
    1.63
    ulously
    1.58
    Act Density 0.101%

    No Known Activations