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

    Neuronpedia

    INDEX
    Explanations

    Round

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    μέν
    -0.07
     polish
    -0.07
    ofil
    -0.06
    ementia
    -0.06
     slaughtered
    -0.06
    OCKET
    -0.06
    eração
    -0.06
    šil
    -0.06
    фици
    -0.06
    configs
    -0.06
    POSITIVE LOGITS
    >{"
    0.07
     distingu
    0.07
     Upgrade
    0.07
    Email
    0.07
    \↵
    0.06
    IO
    0.06
     NotImplementedException
    0.06
     зі
    0.06
     printing
    0.06
     معنی
    0.06
    Act Density 0.001%

    No Known Activations