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

    Neuronpedia

    INDEX
    Explanations

    3

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	al
    -0.07
     Aly
    -0.06
    aras
    -0.06
    sylvania
    -0.06
     pylint
    -0.06
     imper
    -0.06
     Müdürlüğü
    -0.06
     doe
    -0.06
     Kansas
    -0.06
     multimedia
    -0.06
    POSITIVE LOGITS
    VERAGE
    0.07
    DetailsService
    0.07
     lotion
    0.06
    λα
    0.06
    ху
    0.06
    ephir
    0.06
     REQUIRE
    0.06
    اجات
    0.06
     #####
    0.06
    >()↵↵
    0.06
    Act Density 0.000%

    No Known Activations