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

    Neuronpedia

    INDEX
    Explanations

    teaching students lessons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bitrate
    0.47
     regex
    0.43
     denote
    0.42
     regress
    0.42
     idiosyncratic
    0.42
     execute
    0.42
     namespaces
    0.41
     horde
    0.41
     execution
    0.40
     resorting
    0.40
    POSITIVE LOGITS
     lesson
    0.96
     curriculum
    0.96
     curricular
    0.96
     classroom
    0.95
    Students
    0.91
     students
    0.91
    授業
    0.88
    课堂
    0.87
     Curriculum
    0.87
     الطلاب
    0.86
    Act Density 0.020%

    No Known Activations