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

    Neuronpedia

    INDEX
    Explanations

    wear gloves and clothing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ያላቸው
    0.43
    几何
    0.42
     ফটোগ্রাফ
    0.40
    impress
    0.39
    配备
    0.39
     ấn
    0.39
    อุปกรณ์
    0.39
     হত্যা
    0.39
    emptyset
    0.38
    AndUpdate
    0.38
    POSITIVE LOGITS
     gloves
    0.42
    warts
    0.42
     noches
    0.41
     describ
    0.39
    不怕
    0.39
    벤
    0.39
     Lor
    0.39
     Саша
    0.38
    wes
    0.38
     gehen
    0.38
    Act Density 0.037%

    No Known Activations