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

    Neuronpedia

    INDEX
    Explanations

    his possessive pronoun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     yourselves
    0.84
    她们
    0.83
     करेंगी
    0.70
    妳
    0.65
     deren
    0.65
    它们的
    0.65
     इनके
    0.61
    yourself
    0.59
     தெரிவித்தனர்
    0.57
     deles
    0.56
    POSITIVE LOGITS
     his
    3.50
    他的
    3.14
     그의
    3.14
     его
    3.09
     jego
    2.97
    his
    2.89
     hänen
    2.84
     เขา
    2.69
     그는
    2.69
    彼の
    2.69
    Act Density 0.112%

    No Known Activations