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

    Neuronpedia

    INDEX
    Explanations

    simultaneous actions with 'while'

    np_acts-logits-general · gemini-2.5-flash-lite

    while clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    л
    1.03
    ani
    0.94
    2
    0.89
    in
    0.84
    在
    0.84
    ane
    0.82
    ที่
    0.82
    ﺮ
    0.80
    ש
    0.78
    3
    0.77
    POSITIVE LOGITS
    t
    1.16
    و
    1.09
    r
    0.92
    ية
    0.88
    y
    0.86
    ről
    0.84
    c
    0.80
     while
    0.79
     on
    0.77
    ్య
    0.76
    Act Density 0.073%

    No Known Activations