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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    begin
    -0.07
    orca
    -0.07
     größer
    -0.07
    收获
    -0.07
     bakeka
    -0.07
    룅
    -0.07
    itoris
    -0.07
     celui
    -0.07
     KDE
    -0.07
    iOS
    -0.07
    POSITIVE LOGITS
     Commands
    0.07
     Working
    0.07
     Mand
    0.07
     Industry
    0.07
    ,Q
    0.07
    (queue
    0.06
    很重要的
    0.06
     PROJECT
    0.06
     TRADE
    0.06
    젱
    0.06
    Act Density 0.003%

    No Known Activations