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

    Neuronpedia

    INDEX
    Explanations

    but / contrastive conjunction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Microsoft
    0.32
    ^{*}}{\
    0.31
    ాల
    0.28
    ಾಲ
    0.27
    MEX
    0.27
    "*
    0.27
     MongoClient
    0.26
    ABCDEFGHIJKLMNOP
    0.26
    ۞
    0.25
    Deck
    0.25
    POSITIVE LOGITS
     but
    0.64
     pero
    0.57
     αλλά
    0.57
     אבל
    0.55
    but
    0.54
     പക്ഷേ
    0.53
     కానీ
    0.53
     लेकिन
    0.51
     però
    0.50
     لكن
    0.50
    Act Density 0.005%

    No Known Activations