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

    Neuronpedia

    INDEX
    Explanations

    pronoun "them"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     തന്റെ
    0.91
    인의
    0.90
    자의
    0.90
     자신의
    0.90
    自身の
    0.89
    サービスの
    0.87
     પોતાની
    0.83
     함수의
    0.83
     своей
    0.80
    নিজের
    0.80
    POSITIVE LOGITS
     them
    7.40
    them
    6.14
     них
    5.71
     Them
    5.53
     THEM
    5.25
     ними
    5.16
     mereka
    4.75
     ihnen
    4.61
     آنها
    4.48
     тях
    4.25
    Act Density 0.837%

    No Known Activations