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

    Neuronpedia

    INDEX
    Explanations

    demographics and specific topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    我们
    0.52
     我们
    0.45
     (--
    0.42
     为
    0.41
     빠르게
    0.41
     শিশুরা
    0.41
    瀣
    0.41
     +
    0.40
    ithin
    0.40
    猞
    0.39
    POSITIVE LOGITS
     консульта
    0.47
     Kommentar
    0.46
    consult
    0.44
    call
    0.43
    inicial
    0.43
     disfraz
    0.43
     юриди
    0.43
    班
    0.43
     práv
    0.42
    ﻛ
    0.41
    Act Density 0.008%

    No Known Activations