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

    Neuronpedia

    INDEX
    Explanations

    education and degrees

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ،
    0.80
    ;
    0.75
     detriment
    0.73
     in
    0.69
     -
    0.66
    、
    0.63
     pituitary
    0.61
     σε
    0.60
     leftovers
    0.60
     expectant
    0.57
    POSITIVE LOGITS
    т
    0.65
     Masai
    0.61
    o
    0.61
    frü
    0.60
    ro
    0.59
    t
    0.58
     häufig
    0.57
     મોટા
    0.57
     පුද්ග
    0.57
    attended
    0.57
    Act Density 0.002%

    No Known Activations