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

    Neuronpedia

    INDEX
    Explanations

    rupture

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    3
    1.59
    st
    1.30
    2
    1.23
    ن
    1.17
    },
    1.11
    לי
    1.07
    \
    1.06
    room
    1.03
    5
    1.02
    ت
    1.01
    POSITIVE LOGITS
    า
    1.46
     to
    1.23
    o
    1.20
    arı
    1.14
    лся
    0.97
    다면
    0.96
    다
    0.96
    सँग
    0.95
     불구하고
    0.95
    ка
    0.94
    Act Density 0.000%

    No Known Activations