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
    .credentials
    -0.07
     rych
    -0.07
     расп
    -0.06
    .lesson
    -0.06
    #####
    -0.06
    -home
    -0.06
     Εξ
    -0.06
     builtin
    -0.06
    аф
    -0.06
     divorce
    -0.06
    POSITIVE LOGITS
     έως
    0.06
    income
    0.06
    ?)↵↵
    0.06
     know
    0.06
    属于
    0.06
     skyrocket
    0.06
     deutsch
    0.06
    ILTER
    0.06
     caught
    0.06
     propel
    0.05
    Act Density 0.062%

    No Known Activations