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

    Neuronpedia

    INDEX
    Explanations

    before serving

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    數據
    0.33
    ㅋㅋㅋㅋㅋㅋㅋㅋ
    0.32
    按照
    0.32
     사용할
    0.31
    建立
    0.30
     firstly
    0.29
     مسئول
    0.29
    原则
    0.29
    标志
    0.29
    機関
    0.29
    POSITIVE LOGITS
     dismay
    0.36
     yan
    0.33
     su
    0.33
     Bu
    0.31
     Ya
    0.31
     Yan
    0.31
     éste
    0.31
    though
    0.31
     Gets
    0.31
    gets
    0.30
    Act Density 0.002%

    No Known Activations