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

    Neuronpedia

    INDEX
    Explanations

    Parentheses and brackets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .PLL
    -0.07
     Hundred
    -0.07
     요청
    -0.06
     Monaco
    -0.06
    iset
    -0.06
     Merrill
    -0.06
    /******************************************************************************/↵
    -0.06
    ुप
    -0.06
     Beverly
    -0.06
    香蕉
    -0.06
    POSITIVE LOGITS
     зависим
    0.06
     india
    0.06
     اتاق
    0.06
    結果
    0.06
     spinning
    0.06
    ﺔ
    0.06
     гот
    0.06
     человека
    0.06
    _the
    0.06
    deo
    0.06
    Act Density 0.129%

    No Known Activations