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

    Neuronpedia

    INDEX
    Explanations

    satisfaction and happiness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    К
    0.72
    କ
    0.66
    ଓ
    0.59
    এ
    0.57
    ଭ
    0.57
    ప్ర
    0.57
    ش
    0.57
    airs
    0.56
    害怕
    0.56
    ଗ
    0.55
    POSITIVE LOGITS
     Satisfaction
    1.18
     satisfied
    1.14
     satisfaction
    1.06
     Satisf
    1.02
    満足
    0.98
     만족
    0.96
     satisf
    0.96
     zufrieden
    0.96
     satisfacción
    0.93
     zadovol
    0.93
    Act Density 0.034%

    No Known Activations