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

    Neuronpedia

    INDEX
    Explanations

    birth and place names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ла
    0.94
    મ
    0.88
    述べ
    0.85
    ۔
    0.85
    ס
    0.84
    ای
    0.84
    on
    0.83
     фигур
    0.81
    ພວກເຮົາ
    0.80
     infringe
    0.80
    POSITIVE LOGITS
     birth
    1.28
     lahir
    1.27
     Birth
    1.25
     BIRTH
    1.15
     nascita
    1.05
    出生
    1.03
     जन्म
    1.02
    birth
    1.02
    lahir
    1.02
     births
    0.98
    Act Density 0.015%

    No Known Activations