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

    Neuronpedia

    INDEX
    Explanations

    each one of them

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Schluß
    -2.14
    3
    -1.84
    0
    -1.75
     nuovo
    -1.70
    戕
    -1.70
    -1.70
    вгений
    -1.69
    臜
    -1.67
     другую
    -1.67
     '
    -1.67
    POSITIVE LOGITS
     of
    1.91
    棪
    1.90
     المقبل
    1.86
    塤
    1.85
    开来
    1.80
    ศึกษา
    1.77
     histórias
    1.75
     الداخلية
    1.71
     perbuatan
    1.68
    及其
    1.66
    Act Density 0.002%

    No Known Activations