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

    Neuronpedia

    INDEX
    Explanations

    He and his

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     নিজেদের
    0.77
     करेंगी
    0.76
     कहती
    0.73
     کرتی
    0.66
    ходила
    0.66
     themselves
    0.65
     xinh
    0.65
     होंगी
    0.63
     została
    0.63
     نفسها
    0.63
    POSITIVE LOGITS
     himself
    2.20
     his
    1.41
     نفسه
    1.32
    他的
    1.30
     его
    1.29
     그의
    1.23
     sám
    1.23
     Himself
    1.21
    his
    1.20
    彼は
    1.17
    Act Density 0.027%

    No Known Activations