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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and names, particularly related to people and places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    names and foreign words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    urgy
    -0.39
    vinfos
    -0.34
    メント
    -0.32
     Guten
    -0.32
     tele
    -0.32
    件
    -0.32
    inous
    -0.32
     Nou
    -0.32
     Oru
    -0.32
     FICTION
    -0.31
    POSITIVE LOGITS
    saraba
    0.58
     שוליים
    0.57
     InputDecoration
    0.56
    ArgumentParser
    0.56
    脚注の使い方
    0.55
    #+#
    0.55
    tvguidetime
    0.52
    Referanser
    0.49
     Italijanski
    0.48
    ագրություններ
    0.47
    Act Density 0.154%

    No Known Activations