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

    Neuronpedia

    INDEX
    Explanations

    starts with because

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Поэтому
    0.38
    Basically
    0.34
    Therefore
    0.34
     вот
    0.34
     Basically
    0.34
     fantas
    0.34
    Спасибо
    0.34
    Вот
    0.33
    например
    0.33
     Örneğin
    0.33
    POSITIVE LOGITS
     answer
    0.31
     skimage
    0.30
    jr
    0.29
     whiskers
    0.29
    ca
    0.29
    cier
    0.29
    AVA
    0.29
    ruvate
    0.29
     uncoated
    0.29
    gt
    0.28
    Act Density 0.003%

    No Known Activations