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

    Neuronpedia

    INDEX
    Explanations

    Accumulation, videos, murder, personal space

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    佢
    1.32
    ﹗
    1.27
     organisers
    1.24
    ทางการ
    1.24
    囝
    1.19
     peny
    1.09
    スケジュール
    1.09
     schemes
    1.07
    ด้อ
    1.07
     scheme
    1.07
    POSITIVE LOGITS
    7
    4.31
    8
    4.04
    6
    3.93
    9
    3.77
    5
    3.74
    4
    3.68
    3
    3.56
    0
    3.19
    ۷
    2.87
    ٧
    2.85
    Act Density 0.054%

    No Known Activations