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

    Neuronpedia

    INDEX
    Explanations

    phrases starting with 'during'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ש
    0.79
    ের
    0.77
    ू
    0.76
    ி
    0.73
    다
    0.72
     fluorescent
    0.71
    ৬
    0.71
    ی
    0.71
    스
    0.71
    ர்
    0.70
    POSITIVE LOGITS
    t
    1.00
    will
    0.83
    a
    0.82
    е
    0.82
    k
    0.77
    f
    0.73
    fte
    0.68
    During
    0.67
     averiguar
    0.66
    Durante
    0.66
    Act Density 0.023%

    No Known Activations