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

    Neuronpedia

    INDEX
    Explanations

    explaining a concept or fact

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Heute
    0.46
    ሮችን
    0.41
    ườn
    0.39
    andaag
    0.38
    ütfen
    0.38
    攏
    0.38
     কতকগুলি
    0.37
    오늘은
    0.36
    ાર્
    0.36
    طلق
    0.36
    POSITIVE LOGITS
     faptul
    1.04
     наличие
    1.00
     the
    0.92
     adanya
    0.92
     Tatsache
    0.87
     its
    0.84
    那個
    0.82
     having
    0.80
    它的
    0.79
     отсутствие
    0.78
    Act Density 0.093%

    No Known Activations