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

    Neuronpedia

    INDEX
    Explanations

    updates automatically

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.28
     of
    0.24
     của
    0.21
     ഒഴിവാ
    0.19
    of
    0.19
     этих
    0.19
    ni
    0.19
    rian
    0.19
     {
    0.18
    ä
    0.18
    POSITIVE LOGITS
    ת
    0.23
     быстрее
    0.23
     spectacularly
    0.22
     smoothly
    0.21
    起来
    0.20
    随着
    0.20
     временем
    0.20
     سریع
    0.20
    大きく
    0.20
     빠르게
    0.20
    Act Density 1.357%

    No Known Activations