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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.87
    PerformLayout
    -0.68
     <=",
    -0.65
    ]._
    -0.65
    tagHelper
    -0.62
    findpost
    -0.62
    BagLayout
    -0.62
    orical
    -0.60
    Take
    -0.59
    vité
    -0.59
    POSITIVE LOGITS
     Мексичка
    0.45
     fotográfica
    0.44
    PasswordField
    0.40
     Sons
    0.39
    Còn
    0.39
     Elden
    0.38
    những
    0.38
     otomatig
    0.37
    存于互联网档案馆
    0.37
    englanniksi
    0.36
    Act Density 0.004%

    No Known Activations