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

    Neuronpedia

    INDEX
    Explanations

    "No" followed by "-"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     获取
    0.48
    캘
    0.48
    特朗普
    0.47
     శరీ
    0.47
    슌
    0.46
    បង្កើត
    0.45
    ួល
    0.45
    اديم
    0.45
    用户信息
    0.45
     alır
    0.44
    POSITIVE LOGITS
    as
    0.49
    ع
    0.43
    る
    0.43
    って
    0.42
     waged
    0.42
    posted
    0.41
    price
    0.41
     signaled
    0.40
    пси
    0.39
    listed
    0.39
    Act Density 0.002%

    No Known Activations