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

    Neuronpedia

    INDEX
    Explanations

    categorized lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    良好
    0.48
     be
    0.46
    疲
    0.45
    是否
    0.44
    IM
    0.43
    NP
    0.42
     as
    0.41
    IR
    0.41
    实施
    0.41
    ELIST
    0.41
    POSITIVE LOGITS
     collusion
    0.48
     Sebelum
    0.47
    pessoa
    0.45
    Ссы
    0.44
    微软雅黑
    0.43
     Pada
    0.43
    isiä
    0.43
    鹿児
    0.43
     lemongrass
    0.43
     satirical
    0.42
    Act Density 0.000%

    No Known Activations