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

    Neuronpedia

    INDEX
    Explanations

    and then the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Тем
    0.39
     격
    0.38
     оси
    0.37
    キュー
    0.36
    どもの
    0.35
    banners
    0.34
     worldRank
    0.34
     unitary
    0.34
     格
    0.34
     ዲ
    0.33
    POSITIVE LOGITS
     Kib
    0.41
     Ceren
    0.41
     Nan
    0.41
     Gabriele
    0.40
     Corb
    0.39
     Toshiba
    0.39
     शार
    0.37
    Rob
    0.37
    켄
    0.36
    Tib
    0.36
    Act Density 0.009%

    No Known Activations