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

    Neuronpedia

    INDEX
    Explanations

    оставить, отдохнуть

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    🈺
    0.65
    احث
    0.60
     statunitense
    0.59
    纽约
    0.58
    ementerian
    0.58
     statunit
    0.58
    🏈
    0.57
    굉
    0.56
    ناصر
    0.55
    ającą
    0.55
    POSITIVE LOGITS
     с
    0.67
     С
    0.66
     вы
    0.64
     для
    0.63
     от
    0.62
     об
    0.59
     Для
    0.59
     Khark
    0.59
    З
    0.59
     пере
    0.58
    Act Density 0.015%

    No Known Activations