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

    Neuronpedia

    INDEX
    Explanations

    a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cũng
    1.09
    );
    1.08
     ή
    1.06
     веке
    1.05
     hoặc
    1.04
     также
    1.03
     البته
    0.99
     Đặc
    0.98
     asimismo
    0.98
     Пусть
    0.97
    POSITIVE LOGITS
     sekal
    1.05
     tokamaks
    0.99
    اونلو
    0.95
    लभ
    0.94
    لاء
    0.92
     dangereux
    0.91
     나서
    0.91
    蚪
    0.91
    perturbative
    0.90
     considerazione
    0.90
    Act Density 0.202%

    No Known Activations