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

    Neuronpedia

    INDEX
    Explanations

    best

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gó
    -0.08
    Boa
    -0.08
    devices
    -0.07
    _FACTORY
    -0.07
    Carn
    -0.07
     pases
    -0.07
     manufacturer's
    -0.07
     devices
    -0.07
     BAR
    -0.07
    Scanner
    -0.07
    POSITIVE LOGITS
     arkadaş
    0.10
     বন্ধু
    0.10
    朋友
    0.10
     friends
    0.10
    好友
    0.09
     मित्र
    0.09
     મિત્રો
    0.09
     Freunden
    0.09
     친구
    0.09
     друзья
    0.09
    Act Density 0.017%

    No Known Activations