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

    Neuronpedia

    INDEX
    Explanations

    integer division `//`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bạn
    0.81
    是为了
    0.78
    nın
    0.77
    hü
    0.76
    是你
    0.75
    س
    0.73
     Datuk
    0.72
    ından
    0.71
    Ƒ
    0.71
     macam
    0.71
    POSITIVE LOGITS
    ان
    0.89
    us
    0.83
    I
    0.79
    1
    0.77
    な
    0.76
    he
    0.73
    ent
    0.73
    ே
    0.73
    一
    0.72
    all
    0.72
    Act Density 0.002%

    No Known Activations