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

    Neuronpedia

    INDEX
    Explanations

    poor qualities or states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ião
    0.43
     fuerte
    0.42
    ي
    0.41
    פקי
    0.40
     impeccable
    0.40
     число
    0.39
     amplo
    0.39
     positivas
    0.38
    த்ரே
    0.38
    ప్ర
    0.38
    POSITIVE LOGITS
     quality
    0.59
     excuse
    0.56
     workmanship
    0.56
     jakości
    0.55
    quality
    0.53
     calidad
    0.52
     کیفیت
    0.51
     performing
    0.51
     eyesight
    0.50
     prognosis
    0.50
    Act Density 0.004%

    No Known Activations