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

    Neuronpedia

    INDEX
    Explanations

    we or they in different languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ലാ
    0.82
    รือ
    0.78
    Consult
    0.77
     असल्यास
    0.74
     भेड़
    0.73
     കണ്ടെത്ത
    0.72
    是否存在
    0.71
     мел
    0.71
    大幅
    0.69
    सरकारी
    0.69
    POSITIVE LOGITS
    ที่เรา
    1.14
     chúng
    1.05
     theyre
    1.04
     we
    1.03
    我们
    0.99
     이렇게
    0.95
     우리가
    0.93
     they
    0.93
     이제
    0.93
     мы
    0.90
    Act Density 0.000%

    No Known Activations