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

    Neuronpedia

    INDEX
    Explanations

    pronouns them they

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dessen
    0.80
    Its
    0.79
    它的
    0.69
     its
    0.69
     Its
    0.67
     उसकी
    0.64
     esso
    0.64
    因为它
    0.64
     അതിന്റെ
    0.63
    its
    0.61
    POSITIVE LOGITS
    它们
    2.81
    它們
    2.47
     them
    2.31
     mereka
    2.23
     тях
    2.23
     них
    2.20
     they
    2.09
    他们
    2.08
     они
    2.08
     onları
    2.05
    Act Density 0.132%

    No Known Activations