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
     потер
    -0.08
    ucs
    -0.07
    сен
    -0.06
     proxy
    -0.06
    Closure
    -0.06
    سين
    -0.06
     Birth
    -0.06
    وق
    -0.06
    Vir
    -0.06
     DropDownList
    -0.06
    POSITIVE LOGITS
     merry
    0.07
    perimental
    0.06
     happier
    0.06
     puan
    0.06
    _PED
    0.06
    _Get
    0.06
     '/';↵
    0.06
     Hebrew
    0.06
    -Tr
    0.06
     dg
    0.06
    Act Density 0.002%

    No Known Activations