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

    Neuronpedia

    INDEX
    Explanations

    charging unit or station

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Дру
    0.62
    ўцаў
    0.59
    akannya
    0.59
    Ар
    0.59
    Не
    0.57
    ینس
    0.57
    Ад
    0.57
     ennemis
    0.57
    ーフ
    0.56
    Audio
    0.56
    POSITIVE LOGITS
     States
    0.75
     ۵
    0.71
    ่
    0.70
    CT
    0.66
     Harris
    0.65
    larını
    0.65
     COURSE
    0.65
    сайт
    0.65
     K
    0.64
    сё
    0.63
    Act Density 0.003%

    No Known Activations