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

    Neuronpedia

    INDEX
    Explanations

    //

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    usement
    -0.07
    ContextHolder
    -0.07
    isplay
    -0.06
    alığı
    -0.06
     податков
    -0.06
     coder
    -0.06
    adastrar
    -0.06
    currentPage
    -0.06
    ovaného
    -0.06
     Fernandez
    -0.06
    POSITIVE LOGITS
     ::=
    0.08
     hearty
    0.07
     район
    0.06
     Unary
    0.06
     clutch
    0.06
    (cost
    0.06
    咨询
    0.06
    	exit
    0.06
    ():
↵
    0.06
    交
    0.06
    Act Density 0.001%

    No Known Activations