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

    Neuronpedia

    INDEX
    Explanations

    pronoun "her"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ሳሪያ
    1.20
    ግዳ
    1.16
    क
    1.08
    tsioon
    1.06
    ุปกรณ์
    1.05
     họa
    1.02
     Qualquer
    1.02
    ILITIES
    1.02
    ド
    1.02
    ف
    1.00
    POSITIVE LOGITS
    .
    1.59
    ?
    1.41
    _
    1.28
    -
    1.23
    '
    1.17
    !
    1.10
     लाया
    1.05
    *
    1.05
    :
    1.01
    vert
    0.97
    Act Density 0.099%

    No Known Activations