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

    Neuronpedia

    INDEX
    Explanations

    input, questions, data formats

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     изготовления
    1.09
    Ар
    0.94
    Игра
    0.94
     ребят
    0.92
    们
    0.92
    Между
    0.92
    Эта
    0.91
    彡
    0.91
     шар
    0.91
     पहुंच
    0.91
    POSITIVE LOGITS
    ting
    1.63
     Into
    1.39
     into
    1.36
    taining
    1.34
    ures
    1.27
     Producing
    1.23
     INTO
    1.23
     vào
    1.21
     इनटू
    1.19
    ಾನ್
    1.16
    Act Density 0.176%

    No Known Activations