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

    Neuronpedia

    INDEX
    Explanations

    inference and estimation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     proposées
    -0.70
     considérée
    -0.67
     consideradas
    -0.65
     considerados
    -0.61
     réalisées
    -0.60
     proposés
    -0.60
    jelaskan
    -0.60
     schermata
    -0.59
     citada
    -0.59
     proposons
    -0.59
    POSITIVE LOGITS
    apimachinery
    0.70
     Aboriginal
    0.67
    vantaged
    0.63
    DeleteBehavior
    0.62
     myſelf
    0.60
     existence
    0.58
    istoitu
    0.57
     sapi
    0.56
     memoized
    0.56
    出自
    0.56
    Act Density 0.386%

    No Known Activations