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

    Neuronpedia

    INDEX
    Explanations

    bought flowers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ceux
    0.79
     બનાવવા
    0.78
    推出
    0.77
     ಕುಟ
    0.76
     対応
    0.74
     সীমাবদ্ধ
    0.74
     필요한
    0.74
     nyní
    0.74
    Located
    0.74
     subset
    0.74
    POSITIVE LOGITS
     очередной
    0.68
     tellement
    0.68
    /
    0.67
     nuovamente
    0.66
     xong
    0.66
     súper
    0.66
     demasi
    0.65
     ilegal
    0.65
     successfully
    0.64
     incorrectly
    0.62
    Act Density 0.512%

    No Known Activations