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

    Neuronpedia

    INDEX
    Explanations

    articles or descriptors for animals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Penh
    0.67
    愴
    0.66
     CVD
    0.63
    国务
    0.62
     vidé
    0.60
     Soder
    0.60
    欳
    0.60
     கதா
    0.59
     गरे
    0.58
    隰
    0.57
    POSITIVE LOGITS
     tiger
    2.22
     owl
    2.18
     shark
    2.17
     rabbit
    2.12
     squirrel
    2.09
     wolf
    2.06
     cheetah
    2.05
     turtle
    1.99
     eagle
    1.98
     dolphin
    1.98
    Act Density 0.240%

    No Known Activations