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

    Neuronpedia

    INDEX
    Explanations

    water and subsequent context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     воздуш
    0.40
     леса
    0.39
    วัต
    0.38
     rozpozn
    0.38
     ඉද
    0.38
    ಮು
    0.37
     মুহাম্মদ
    0.37
     vâr
    0.36
     చిత
    0.36
    ющим
    0.35
    POSITIVE LOGITS
    logged
    1.20
    💧
    0.93
    melon
    0.89
     water
    0.89
    💦
    0.89
     Water
    0.84
    Water
    0.84
    water
    0.83
     droplets
    0.82
    logging
    0.80
    Act Density 0.043%

    No Known Activations