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

    Neuronpedia

    INDEX
    Explanations

    youth

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    盒子
    -0.08
     Worksheets
    -0.08
    oks
    -0.08
    تنسيق
    -0.07
    (Create
    -0.07
     Clerk
    -0.07
    滦
    -0.07
     conservation
    -0.07
     educators
    -0.07
     Validators
    -0.07
    POSITIVE LOGITS
     loro
    0.07
    但他们
    0.07
     modalità
    0.07
    iasco
    0.07
    .*;↵
    0.06
    淡淡
    0.06
     بواسطة
    0.06
    _display
    0.06
    *))
    0.06
    /tree
    0.06
    Act Density 0.006%

    No Known Activations