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

    Neuronpedia

    INDEX
    Explanations

    verbs followed by them

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     می‌کنند
    0.38
    њи
    0.37
     അതിന്റെ
    0.36
    oretically
    0.35
    人之
    0.34
    彼は
    0.34
    명의
    0.34
    方の
    0.33
     মেহে
    0.33
    उस
    0.32
    POSITIVE LOGITS
     them
    3.95
    them
    3.56
     них
    3.11
     Them
    2.81
     THEM
    2.73
     ними
    2.53
     тях
    2.48
     őket
    2.48
     onları
    2.48
    它们
    2.44
    Act Density 0.234%

    No Known Activations