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

    Neuronpedia

    INDEX
    Explanations

    but followed by concessions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nevertheless
    0.63
     kuitenkin
    0.58
     nonetheless
    0.57
     também
    0.56
     also
    0.54
     myös
    0.52
     toutefois
    0.51
     també
    0.51
     Nevertheless
    0.50
    also
    0.48
    POSITIVE LOGITS
     possible
    0.49
     возможно
    0.46
     takže
    0.43
     возможных
    0.43
     widely
    0.41
     posible
    0.41
    可能是
    0.41
    возможно
    0.41
     conceivable
    0.41
    因此
    0.40
    Act Density 0.028%

    No Known Activations