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

    Neuronpedia

    INDEX
    Explanations

    various categories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     եւ
    1.12
     tööt
    1.00
     }}\
    0.97
    azole
    0.97
     и
    0.97
     није
    0.96
     và
    0.96
     နှင့်
    0.95
     és
    0.95
     և
    0.94
    POSITIVE LOGITS
     طبعا
    1.13
     conveniently
    1.06
    ANGMAR
    1.03
     Gratis
    1.02
    Conven
    1.00
    叫做
    1.00
    ۢ
    1.00
     Convenient
    0.97
     aja
    0.96
     حسب
    0.96
    Act Density 0.410%

    No Known Activations