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

    Neuronpedia

    INDEX
    Explanations

    joke

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ＜
    -0.08
    minent
    -0.07
    ník
    -0.06
    
    -0.06
    _school
    -0.06
     آموز
    -0.06
     Armen
    -0.06
     opravdu
    -0.06
    фектив
    -0.06
     equipments
    -0.06
    POSITIVE LOGITS
     joke
    0.09
     rd
    0.07
     ENG
    0.07
     CAP
    0.06
     comedic
    0.06
     informant
    0.06
    They
    0.06
     Loop
    0.06
    .Inv
    0.06
     inevitable
    0.06
    Act Density 0.014%

    No Known Activations