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

    Neuronpedia

    INDEX
    Explanations

    liquids, pouring, and volume

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ینده
    0.61
     terceros
    0.57
     decisiones
    0.55
     flirting
    0.54
     fachada
    0.54
     lapangan
    0.53
     flaw
    0.52
     arras
    0.52
     demographics
    0.52
    Inicio
    0.52
    POSITIVE LOGITS
     Water
    1.01
     water
    1.00
    水
    0.98
    water
    0.92
     पानी
    0.91
     воды
    0.90
     પાણી
    0.89
    水量
    0.88
     gallons
    0.87
    水を
    0.86
    Act Density 0.080%

    No Known Activations