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

    Neuronpedia

    INDEX
    Explanations

    business and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ی
    0.79
    ک
    0.68
    تی
    0.66
    с
    0.61
    گ
    0.60
    ч
    0.59
     to
    0.58
    са
    0.57
    یل
    0.57
    تر
    0.57
    POSITIVE LOGITS
    చేసిన
    0.52
     финансо
    0.51
     Scorpio
    0.50
    }=$
    0.49
    ዎታል
    0.49
     ovarian
    0.49
     Ryanair
    0.48
    zovaniyu
    0.47
     shea
    0.47
    }$;
    0.47
    Act Density 2.560%

    No Known Activations