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

    Neuronpedia

    INDEX
    Explanations

    numbers followed by the word 'patients'

    oai_token-act-pair · gemini-2.0-flash

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    出版年
    -0.67
     rhestr
    -0.63
    ┬
    -0.56
    ollectionView
    -0.53
    crollView
    -0.53
     aben
    -0.51
    fino
    -0.50
     strongest
    -0.49
     dozen
    -0.49
    Catégorie
    -0.49
    POSITIVE LOGITS
     سكانية
    0.69
    دانشنامهٔ
    0.62
    portál
    0.62
    AndEndTag
    0.59
    Referanser
    0.59
     Italijanski
    0.57
    KommentareTeilen
    0.57
    prüche
    0.56
     pinulongan
    0.56
     Réponses
    0.56
    Act Density 0.180%

    No Known Activations