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

    Neuronpedia

    INDEX
    Explanations

    these

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    headline
    0.44
    รวม
    0.39
    cinas
    0.39
     سمیت
    0.39
    那种
    0.38
    issati
    0.38
    head
    0.37
    Ⅽ
    0.37
    র্ষি
    0.37
    Headline
    0.36
    POSITIVE LOGITS
    these
    0.67
     these
    0.66
    這些
    0.63
     этими
    0.62
    これらの
    0.57
     هذه
    0.56
    These
    0.55
     questi
    0.55
     aceste
    0.55
     These
    0.53
    Act Density 0.002%

    No Known Activations