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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Rabbit
    -0.08
     insight
    -0.06
    pickup
    -0.06
     přímo
    -0.06
    Met
    -0.06
     Craft
    -0.06
     Rum
    -0.06
    _gui
    -0.06
     вик
    -0.06
    (Screen
    -0.06
    POSITIVE LOGITS
    ,ep
    0.07
    Our
    0.07
     tienes
    0.07
    زو
    0.07
    ]):
    0.06
     FW
    0.06
     Fitness
    0.06
    Dealer
    0.06
     oauth
    0.06
     переб
    0.06
    Act Density 0.002%

    No Known Activations