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

    Neuronpedia

    INDEX
    Explanations

    Starting responses with "Okay"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ticked
    0.75
     vacuoles
    0.72
    ளுடைய
    0.72
     plunged
    0.70
     REV
    0.68
    ﹡
    0.67
    搏
    0.67
     প্রতিহিংস
    0.67
     vacuum
    0.66
     الأمريكية
    0.66
    POSITIVE LOGITS
     Ano
    0.84
    Ano
    0.79
     Hala
    0.72
     Oy
    0.68
     ano
    0.66
     Di
    0.66
     పా
    0.65
     প্রতিবেদনে
    0.65
    Gr
    0.64
     oi
    0.64
    Act Density 0.041%

    No Known Activations