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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     obey
    -0.07
     حين
    -0.07
     leakage
    -0.06
    	command
    -0.06
    联合
    -0.06
     آهنگ
    -0.06
    getIndex
    -0.06
    ان
    -0.06
     مشاهدة
    -0.06
    ifie
    -0.06
    POSITIVE LOGITS
    #plt
    0.07
     ePub
    0.07
    (exec
    0.07
     Narr
    0.07
    \xaa
    0.07
    ubit
    0.06
    stairs
    0.06
    752
    0.06
     Liter
    0.06
    .nextDouble
    0.06
    Act Density 0.013%

    No Known Activations