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

    Neuronpedia

    INDEX
    Explanations

    Units digit math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ('#
    -0.07
     دين
    -0.07
     děti
    -0.07
    ィ
    -0.06
     حافظه
    -0.06
    섭
    -0.06
     فتح
    -0.06
     дітей
    -0.06
    ソ
    -0.06
    _raises
    -0.06
    POSITIVE LOGITS
     Mund
    0.07
    ้ส
    0.06
    DoubleClick
    0.06
    DataRow
    0.06
     principal
    0.06
    -FIRST
    0.06
    //--
    0.06
    .expires
    0.06
    unnable
    0.06
    กระท
    0.06
    Act Density 0.002%

    No Known Activations