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

    Neuronpedia

    INDEX
    Explanations

    masculine third person subject

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    它们的
    1.08
     delas
    0.88
    arlas
    0.85
    它們
    0.82
     possono
    0.78
    irlas
    0.78
    我的
    0.78
     elas
    0.77
     बढ़ाते
    0.77
    它们
    0.76
    POSITIVE LOGITS
     he
    4.90
     He
    4.75
    He
    4.54
     он
    3.91
     він
    3.66
     그는
    3.52
     তিনি
    3.51
     Он
    3.31
    他
    3.27
    彼は
    3.23
    Act Density 0.141%

    No Known Activations