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

    Neuronpedia

    INDEX
    Explanations

    operating income

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﻤ
    0.87
     on
    0.86
    に基づいて
    0.84
     چون
    0.83
    行う
    0.79
     زیرا
    0.78
    д
    0.75
    ﻨ
    0.73
    ști
    0.73
    ین
    0.71
    POSITIVE LOGITS
    a
    0.80
    -
    0.77
    ’
    0.74
    og
    0.68
     trasera
    0.64
    te
    0.63
    an
    0.62
     Elegant
    0.62
    that
    0.62
    ryk
    0.62
    Act Density 0.000%

    No Known Activations