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

    Neuronpedia

    INDEX
    Explanations

    CIDR notation for IP addresses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    (
    0.70
     consci
    0.59
     spectacularly
    0.57
     typename
    0.56
    =
    0.56
     Bav
    0.55
     of
    0.53
     garr
    0.51
     geme
    0.50
     удиви
    0.50
    POSITIVE LOGITS
    li
    0.66
    ات
    0.65
     பயணிகள்
    0.63
     étaient
    0.63
    ników
    0.63
    ana
    0.63
    е
    0.63
    ni
    0.62
     प्रोटीन
    0.60
     உள்ளனர்
    0.60
    Act Density 0.006%

    No Known Activations