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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    class
    -0.74
    colon
    -0.55
     CreateTagHelper
    -0.53
    PreferredItem
    -0.51
    XmlAccessorType
    -0.51
    addLast
    -0.49
    ilder
    -0.49
     Paling
    -0.49
    curities
    -0.48
    illai
    -0.48
    POSITIVE LOGITS
    }{*}{
    0.58
     EnglishChoose
    0.57
    données
    0.55
    SequentialGroup
    0.54
    orianCalendar
    0.54
    sal
    0.52
    Authors
    0.52
    UNTS
    0.51
    encre
    0.50
    rxjs
    0.50
    Act Density 0.140%

    No Known Activations