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

    Neuronpedia

    INDEX
    Explanations

    course, class, master's degree, studies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     discoloration
    0.71
     hasty
    0.68
     unsightly
    0.68
     momentarily
    0.67
     concealment
    0.67
     deceit
    0.64
     bushes
    0.64
     да
    0.63
     blatant
    0.63
     violated
    0.63
    POSITIVE LOGITS
    课程
    1.52
     coursework
    1.41
     Courses
    1.38
     обучение
    1.35
    研修
    1.30
     curriculum
    1.30
     courses
    1.29
     обучения
    1.27
    学习
    1.26
    學習
    1.25
    Act Density 0.007%

    No Known Activations