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

    Neuronpedia

    INDEX
    Explanations

    grades, scores, and exams

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sauvage
    0.48
     nozzle
    0.46
    購物
    0.46
    専用
    0.45
     frequented
    0.44
     anarch
    0.43
     wsi
    0.43
     diurnal
    0.43
    🌰
    0.43
     nozzles
    0.42
    POSITIVE LOGITS
    成绩
    1.24
    成績
    1.14
     calificaciones
    0.98
     grades
    0.93
     exams
    0.92
    考试
    0.91
    学生的
    0.91
     scores
    0.90
     sınav
    0.90
     Grading
    0.90
    Act Density 0.097%

    No Known Activations