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

    Neuronpedia

    INDEX
    Explanations

    we

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     honom
    0.71
    私の
    0.70
     mógł
    0.68
     असेल
    0.67
     Them
    0.66
    ᄂ
    0.65
    さり
    0.64
    ︡
    0.63
    என்
    0.62
    луйста
    0.61
    POSITIVE LOGITS
     we
    6.76
     chúng
    5.47
     мы
    5.44
    我们
    5.16
    我們
    5.07
     আমরা
    5.05
     우리는
    4.97
    we
    4.94
    We
    4.86
     We
    4.83
    Act Density 1.073%

    No Known Activations