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

    Neuronpedia

    INDEX
    Explanations

    scientific publications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sher
    -0.06
     отправ
    -0.06
    Serialize
    -0.06
     saf
    -0.06
    	x
    -0.06
     hoá
    -0.06
    .star
    -0.06
     sendo
    -0.06
     Jing
    -0.06
     abound
    -0.06
    POSITIVE LOGITS
    #↵
    0.07
    ựa
    0.06
    εδ
    0.06
    іно
    0.06
     دانشنامه
    0.06
     yeri
    0.06
    ısını
    0.06
     используется
    0.06
    ...↵
    0.06
     isnt
    0.06
    Act Density 0.001%

    No Known Activations