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

    Neuronpedia

    INDEX
    Explanations

    giving examples

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    enumi
    -0.62
     vastaan
    -0.53
     løpet
    -0.52
    TRANSLATE
    -0.50
     veille
    -0.50
     brancas
    -0.50
     čier
    -0.49
     quæ
    -0.49
     campanha
    -0.49
     foncé
    -0.49
    POSITIVE LOGITS
     Paglinawan
    0.60
     these
    0.58
    :\/\/
    0.57
    ModelSerializer
    0.56
     '
    0.56
     autorytatywna
    0.55
    GIVEREF
    0.55
    calaure
    0.54
    Portály
    0.54
    AddHtmlAttribute
    0.52
    Act Density 0.042%

    No Known Activations