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

    Neuronpedia

    INDEX
    Explanations

    time and date formats

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    上面的
    1.05
     crook
    0.72
    ڑ
    0.72
     whatnot
    0.71
    க்கூட
    0.68
     שלה
    0.67
     aici
    0.66
    上面
    0.66
     ہماری
    0.66
     करण्याचा
    0.65
    POSITIVE LOGITS
    Category
    1.08
     Category
    1.05
     CATEG
    0.99
    category
    0.96
     categories
    0.93
     category
    0.91
     Categories
    0.91
    CATEG
    0.89
     Categor
    0.88
    Categories
    0.86
    Act Density 0.002%

    No Known Activations