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

    Neuronpedia

    INDEX
    Explanations

    water and associated concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     квали
    0.40
     финанси
    0.39
    วัต
    0.39
    承认
    0.38
     инструкции
    0.38
     tud
    0.38
     инду
    0.38
    调查
    0.38
     conçu
    0.38
     заинтере
    0.37
    POSITIVE LOGITS
    💧
    0.94
     Water
    0.89
    Water
    0.89
     water
    0.86
    💦
    0.86
     droplets
    0.82
     水
    0.75
    melon
    0.75
    logged
    0.74
     वॉटर
    0.73
    Act Density 0.047%

    No Known Activations