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

    Neuronpedia

    INDEX
    Explanations

    say "$"

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     celebrate
    0.64
    ides
    0.61
     জাগ
    0.60
    drawLine
    0.60
    stven
    0.58
    Eight
    0.57
     উপন
    0.57
    葱
    0.57
     அலங்க
    0.56
     decl
    0.56
    POSITIVE LOGITS
     Kegiatan
    0.82
    ว้าง
    0.81
     Evaluación
    0.80
     determinación
    0.77
     esempi
    0.77
     شدند
    0.76
     मेरी
    0.76
    esempio
    0.74
     Tecnología
    0.74
     écrit
    0.72
    Act Density 0.007%

    No Known Activations