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

    Neuronpedia

    INDEX
    Explanations

    academic terms and durations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Barlow
    0.74
    解説
    0.72
     خان
    0.69
     увели
    0.67
    沘
    0.67
    粟
    0.66
     parad
    0.66
     YouTube
    0.65
    抢
    0.65
     قاعدة
    0.64
    POSITIVE LOGITS
     semester
    2.80
     Semester
    2.78
    Semester
    2.73
     term
    2.55
     semesters
    2.51
    semester
    2.50
    Term
    2.47
     Term
    2.34
    term
    2.28
     sem
    2.19
    Act Density 0.089%

    No Known Activations