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

    Neuronpedia

    INDEX
    Explanations

    analyzed with, we explore, lead to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    褛
    0.52
     Psychiatry
    0.52
    하거나
    0.52
     vagy
    0.52
    鹑
    0.50
    acariy
    0.50
    瑷
    0.50
    鲔
    0.50
    akespeare
    0.48
     завтра
    0.48
    POSITIVE LOGITS
    Ⅰ
    0.70
     丨
    0.68
    arrerol
    0.67
    丨
    0.66
    Ⅲ
    0.62
    Zhang
    0.61
     monotonous
    0.61
     Xia
    0.59
    Ⅴ
    0.59
    Ⅱ
    0.59
    Act Density 0.028%

    No Known Activations