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

    Neuronpedia

    INDEX
    Explanations

    planning financial code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ullahi
    0.47
     водо
    0.45
    摸
    0.42
    ುಕ
    0.41
     Brands
    0.41
    َى
    0.41
    需
    0.41
    튿
    0.41
    uli
    0.41
    面上
    0.40
    POSITIVE LOGITS
    beth
    0.54
     برای
    0.53
     outflow
    0.51
    ی
    0.51
    s
    0.51
     ارب
    0.50
    '
    0.50
     heroism
    0.50
    를
    0.50
    برای
    0.49
    Act Density 0.000%

    No Known Activations