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

    Neuronpedia

    INDEX
    Explanations

    moral ambiguity, conflict, and compromise

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ।
    1.23
    ש
    1.15
    ال
    1.10
    yr
    1.09
    ع
    1.07
    th
    1.05
    ח
    1.04
    uk
    1.03
    dl
    1.03
    d
    1.03
    POSITIVE LOGITS
    <0x80>
    1.05
    })$,
    0.82
    чи
    0.80
    ách
    0.79
     Бүген
    0.79
     denomin
    0.76
     Bruder
    0.73
     on
    0.72
     Vicar
    0.72
     Gazi
    0.72
    Act Density 0.011%

    No Known Activations