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

    Neuronpedia

    INDEX
    Explanations

    reiteration of points

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     مک
    0.41
     similarly
    0.41
    正如
    0.40
    如下
    0.39
     Gregorio
    0.39
     hatt
    0.39
    のだろう
    0.37
     ,
    0.37
     effectivement
    0.37
     hil
    0.37
    POSITIVE LOGITS
     это
    0.51
     aici
    0.45
     является
    0.44
     meravigli
    0.42
    nilai
    0.41
    ણ
    0.41
     ഇത്
    0.41
     आहे
    0.41
    あくまで
    0.40
    ain
    0.40
    Act Density 0.053%

    No Known Activations