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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     VERY
    0.79
     très
    0.70
     zwei
    0.69
     THIS
    0.69
     vostre
    0.69
     upped
    0.69
     very
    0.67
     väldigt
    0.67
     nicer
    0.66
     questo
    0.66
    POSITIVE LOGITS
    ورو
    0.49
     الرغم
    0.48
     γεγον
    0.48
     стрем
    0.47
     نش
    0.47
    اتب
    0.47
     כאשר
    0.47
     strive
    0.47
    هدف
    0.47
    Sach
    0.46
    Act Density 0.000%

    No Known Activations