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

    Neuronpedia

    INDEX
    Explanations

    father

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    y
    3.02
    ي
    2.92
    smanship
    2.13
    י
    2.11
     Crore
    1.87
    m
    1.87
    يًا
    1.84
    ри
    1.83
    yang
    1.81
    il
    1.79
    POSITIVE LOGITS
    。
    2.05
     encarg
    1.88
    '*
    1.84
    基づ
    1.82
    ة
    1.82
    ণ
    1.80
    이라고
    1.80
     demasi
    1.79
    のは
    1.77
     danneggi
    1.77
    Act Density 0.034%

    No Known Activations