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

    Neuronpedia

    INDEX
    Explanations

    in the form of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     দা
    0.48
    providecommand
    0.43
     सक्रिय
    0.40
     Sachen
    0.40
     davon
    0.40
     મારા
    0.40
     assurer
    0.39
    炘
    0.39
     सेकेंडरी
    0.38
    棫
    0.38
    POSITIVE LOGITS
     format
    0.93
    形式
    0.92
     berupa
    0.89
     вигляді
    0.88
     berbentuk
    0.87
     형태로
    0.84
    格式
    0.80
     формате
    0.80
     формат
    0.77
    format
    0.77
    Act Density 0.217%

    No Known Activations