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

    Neuronpedia

    INDEX
    Explanations

    pronoun he

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Their
    1.72
     Their
    1.69
    它们的
    1.67
     их
    1.51
     their
    1.50
    他们的
    1.49
    their
    1.47
    他們的
    1.46
     їх
    1.44
    उनकी
    1.43
    POSITIVE LOGITS
     he
    6.74
     он
    5.49
     він
    4.99
     그는
    4.59
     তিনি
    4.34
    He
    4.23
    他
    4.11
    彼は
    4.07
     He
    4.07
    he
    3.99
    Act Density 0.179%

    No Known Activations