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

    Neuronpedia

    INDEX
    Explanations

    other languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ۲۸
    -0.07
    oksen
    -0.06
    ObjectId
    -0.06
     는
    -0.06
    Authorization
    -0.06
     everlasting
    -0.06
     قیمت
    -0.06
    ยาว
    -0.06
    _parameters
    -0.06
     eternal
    -0.06
    POSITIVE LOGITS
     gerek
    0.06
    姆
    0.06
    ,,,,,,,,
    0.06
    Contained
    0.06
    $template
    0.06
    得到
    0.06
     devastated
    0.06
    했
    0.06
    �
    0.06
    .tbl
    0.06
    Act Density 0.033%

    No Known Activations