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

    Neuronpedia

    INDEX
    Explanations

    concepts of progress and growth

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.64
    /
    0.63
     শুধুমাত্র
    0.56
     hoặc
    0.55
    ).
    0.53
     motorcycle
    0.51
     veya
    0.51
     arba
    0.50
     (
    0.50
     either
    0.49
    POSITIVE LOGITS
    پے
    0.59
    angkah
    0.59
     沈
    0.58
    那边
    0.57
    തില്‍
    0.57
     sparsim
    0.57
    Ｃ
    0.55
    Ｉ
    0.55
    recall
    0.55
     ഏറെ
    0.55
    Act Density 0.161%

    No Known Activations