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
    aarrggbb
    -0.70
     bezeichneter
    -0.69
    tagHelperRunner
    -0.65
    didSet
    -0.64
    verwijspagina
    -0.63
    keyColumn
    -0.63
    XmlAccessType
    -0.63
     kaynağından
    -0.63
    AddTagHelper
    -0.61
    #+#
    -0.61
    POSITIVE LOGITS
     publico
    0.56
    HtmlAttribute
    0.54
    ATORS
    0.51
     vastaan
    0.51
     heureuse
    0.50
    eridge
    0.49
    ators
    0.48
    chale
    0.48
     heb
    0.47
     rada
    0.47
    Act Density 0.006%

    No Known Activations