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

    Neuronpedia

    INDEX
    Explanations

    where

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ко
    -0.07
     до
    -0.06
     infused
    -0.06
     sàn
    -0.06
    atitude
    -0.06
    p
    -0.06
     believable
    -0.06
     genitals
    -0.06
     chefs
    -0.06
    节
    -0.06
    POSITIVE LOGITS
    普通
    0.07
    _userid
    0.07
     inet
    0.07
    Democrats
    0.07
    懂
    0.07
     AssemblyCompany
    0.07
    oreferrer
    0.07
     INTERRUPTION
    0.07
    ‌پدیای
    0.07
    _Resource
    0.06
    Act Density 0.013%

    No Known Activations