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

    Neuronpedia

    INDEX
    Explanations

    of course

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Specifically
    0.92
    的是
    0.90
    Specifically
    0.90
    specifically
    0.86
     какая
    0.85
     odnosno
    0.84
     بشكل
    0.82
    这是一个
    0.78
     zarówno
    0.77
    SOME
    0.77
    POSITIVE LOGITS
     course
    1.77
    course
    1.40
     whom
    1.20
     these
    1.16
     those
    1.11
     COURSE
    1.11
     sorts
    1.09
     interest
    1.05
     Course
    1.04
    Course
    1.04
    Act Density 0.141%

    No Known Activations