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

    Neuronpedia

    INDEX
    Explanations

    despite

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     puisqu
    0.44
     щоб
    0.44
    เพื่อ
    0.42
     כדי
    0.41
     Bởi
    0.41
     чтобы
    0.40
    Imagine
    0.39
     poprzez
    0.39
     ដើម្បី
    0.38
     zullen
    0.38
    POSITIVE LOGITS
     despite
    0.71
    despite
    0.58
     несмотря
    0.57
     Despite
    0.56
     apesar
    0.54
     trotz
    0.53
     رغم
    0.50
     हालांकि
    0.48
     nonostante
    0.47
     obwohl
    0.46
    Act Density 0.062%

    No Known Activations