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

    Neuronpedia

    INDEX
    Explanations

    career paths and planning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0
    2.02
    ру
    1.61
    ма
    1.56
    ق
    1.54
    ra
    1.52
    ع
    1.46
    ip
    1.45
    9
    1.45
    ها
    1.42
    nya
    1.41
    POSITIVE LOGITS
    में
    1.59
    也就
    1.57
     Як
    1.54
    ihe
    1.53
    க்கழக
    1.48
    驛
    1.43
    知道了
    1.41
    ሳሪያ
    1.41
    创作
    1.40
     Grâce
    1.38
    Act Density 0.009%

    No Known Activations