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

    Neuronpedia

    INDEX
    Explanations

    so

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     यात
    0.74
     이때
    0.72
     없음
    0.70
     سپس
    0.68
    పాటు
    0.66
     hingegen
    0.63
    的就是
    0.63
     यामध्ये
    0.61
     чрезвы
    0.61
     څر
    0.61
    POSITIVE LOGITS
     so
    6.81
    So
    5.30
    so
    5.28
     So
    5.16
     soooo
    4.36
     sooo
    4.22
     socalled
    4.19
     så
    4.14
     soo
    3.67
     так
    3.60
    Act Density 1.059%

    No Known Activations