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

    Neuronpedia

    INDEX
    Explanations

    recently, thoroughly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     оплаты
    0.45
    你會
    0.43
    ที่คุณ
    0.42
     Кстати
    0.41
    unread
    0.40
    getBlue
    0.40
    看不到
    0.39
    你会
    0.39
     مذا
    0.39
    خاص
    0.38
    POSITIVE LOGITS
     recently
    0.75
     recent
    0.62
     recientemente
    0.61
     recentemente
    0.58
     récent
    0.57
     reciente
    0.56
     সম্প্রতি
    0.56
     thoroughly
    0.54
    先日
    0.52
    Recently
    0.52
    Act Density 0.001%

    No Known Activations