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

    Neuronpedia

    INDEX
    Explanations

    childhood

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    「
    0.70
     cũng
    0.70
    及
    0.61
    正
    0.59
    也
    0.59
    本
    0.58
    对
    0.57
    那
    0.57
    要
    0.57
    等
    0.57
    POSITIVE LOGITS
    PMorgan
    0.66
     establecidos
    0.64
    weeney
    0.61
     Verenigde
    0.58
     Перейти
    0.58
     Consultado
    0.57
     жок
    0.57
     فقال
    0.57
     amelyet
    0.57
     {},
    0.57
    Act Density 0.001%

    No Known Activations