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

    Neuronpedia

    INDEX
    Explanations

    gentle licking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     कानून
    0.64
     criminality
    0.62
     преступ
    0.60
     gouvernement
    0.59
    营收
    0.59
     финансо
    0.59
     정책
    0.59
     паліты
    0.59
     політи
    0.58
    权力
    0.58
    POSITIVE LOGITS
     gently
    0.77
     rinsed
    0.70
     moistened
    0.68
     rinse
    0.62
     Gently
    0.61
     water
    0.61
     preso
    0.61
     cooled
    0.60
     rinsing
    0.59
     silicone
    0.59
    Act Density 1.055%

    No Known Activations