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

    Neuronpedia

    INDEX
    Explanations

    in a manner

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     неизвест
    0.42
     beispielsweise
    0.41
    вший
    0.40
    れば
    0.40
    そもそも
    0.39
     tedy
    0.38
    лін
    0.38
    ুই
    0.37
     زیاد
    0.37
    没事
    0.37
    POSITIVE LOGITS
     sambil
    0.82
     באופן
    0.79
     بشكل
    0.79
     방식으로
    0.77
     manière
    0.76
     with
    0.75
     differently
    0.73
    的方式
    0.73
     spôsob
    0.73
     maniera
    0.72
    Act Density 0.041%

    No Known Activations