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

    Neuronpedia

    INDEX
    Explanations

    it

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     is
    -1.30
     it
    -1.23
     was
    -0.98
     has
    -0.82
     It
    -0.79
     isn
    -0.79
     “
    -0.76
     doesn
    -0.76
     wasn
    -0.72
    It
    -0.69
    POSITIVE LOGITS
     pinulongan
    0.88
     مرئيه
    0.87
    contentLoaded
    0.85
    ьаж
    0.84
     تضيفلها
    0.84
    verwijspagina
    0.82
     Мексичка
    0.77
    脚注の使い方
    0.77
    queryInterface
    0.77
     ModelExpression
    0.75
    Act Density 0.069%

    No Known Activations