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

    Neuronpedia

    INDEX
    Explanations

    water and hydration levels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    掸
    0.54
     აღმასრულებელი
    0.48
    ナソニック
    0.47
    გუფი
    0.47
     गैंगस्टर
    0.46
    ﭥ
    0.46
    导演
    0.45
     estím
    0.45
    勫
    0.44
    ዦ
    0.44
    POSITIVE LOGITS
     water
    1.96
     Water
    1.68
     agua
    1.58
     água
    1.57
    water
    1.56
    水
    1.56
    Water
    1.55
     WATER
    1.45
     水
    1.39
     الماء
    1.36
    Act Density 0.121%

    No Known Activations