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

    Neuronpedia

    INDEX
    Explanations

    988 crisis lifeline

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '
    0.93
    ي
    0.86
    í
    0.73
    é
    0.72
     molest
    0.71
    ina
    0.70
    ،
    0.68
     and
    0.65
    انية
    0.64
     Анто
    0.63
    POSITIVE LOGITS
    9
    0.91
     ninth
    0.83
    لی
    0.78
    سین
    0.78
    エ
    0.75
    ९
    0.75
    リ
    0.74
    ⁹
    0.71
    دی
    0.71
    ９
    0.71
    Act Density 0.080%

    No Known Activations