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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    同仁
    -0.07
     ثنائي
    -0.07
    !↵↵↵↵↵↵
    -0.07
    .getSharedPreferences
    -0.07
     Train
    -0.07
    	offset
    -0.07
     Speech
    -0.06
     plt
    -0.06
    @interface
    -0.06
     people
    -0.06
    POSITIVE LOGITS
    яз
    0.08
     diverse
    0.08
    ,{
    0.07
    nex
    0.07
     Haven
    0.07
    搜
    0.07
    seven
    0.07
     Moreover
    0.07
     NYPD
    0.07
     Mia
    0.07
    Act Density 0.017%

    No Known Activations