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

    Neuronpedia

    INDEX
    Explanations

    Language question requests

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     definida
    -0.07
     apropi
    -0.07
     నిర్వ
    -0.07
    brit
    -0.07
     assembly
    -0.07
     ord
    -0.07
     apache
    -0.07
     compiler
    -0.07
    �o
    -0.07
     regres
    -0.07
    POSITIVE LOGITS
     échanges
    0.09
    回应
    0.09
    Здравствуйте
    0.09
     Ami
    0.08
     replies
    0.08
     replied
    0.08
     Replies
    0.08
    äche
    0.08
    еды
    0.08
     модер
    0.08
    Act Density 0.038%

    No Known Activations