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

    Neuronpedia

    INDEX
    Explanations

    roads and highways

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    1.30
    面向
    1.24
    ে
    1.20
     vive
    1.19
    cimento
    1.18
    紺
    1.15
    이드
    1.13
    ,
    1.13
     conjunction
    1.13
    cü
    1.12
    POSITIVE LOGITS
     roads
    2.23
    ﾙ
    2.09
    ৪
    1.88
    ný
    1.88
    nosť
    1.87
    4
    1.86
     Roads
    1.84
    ﺎ
    1.84
    5
    1.78
    ﺮ
    1.76
    Act Density 0.041%

    No Known Activations