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

    Neuronpedia

    INDEX
    Explanations

    un

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Jefus
    -0.70
     myſelf
    -0.69
     himſelf
    -0.65
     Conſ
    -0.64
     purpoſe
    -0.63
     Monfieur
    -0.63
     ſeveral
    -0.62
     CreateTagHelper
    -0.62
    bootstrapcdn
    -0.62
     pleaſure
    -0.60
    POSITIVE LOGITS
    Usual
    0.60
    endregion
    0.57
     ordinaire
    0.54
     conventional
    0.50
     ordinary
    0.50
    ిక
    0.47
     usual
    0.46
    boxing
    0.46
     igual
    0.46
    conventional
    0.45
    Act Density 0.003%

    No Known Activations