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

    Neuronpedia

    INDEX
    Explanations

    assisting in class

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    旗下
    -0.10
     kapsamında
    -0.08
     Giant
    -0.08
     giant
    -0.08
     الدولية
    -0.08
     humana
    -0.08
    hoz
    -0.08
     avaliação
    -0.08
     colossal
    -0.08
     causada
    -0.08
    POSITIVE LOGITS
    Chosen
    0.09
     Rotate
    0.09
     elegido
    0.09
     선정
    0.08
    .selected
    0.08
     Rotation
    0.08
    selected
    0.08
    	selected
    0.08
     chosen
    0.08
     തെരഞ്ഞെട
    0.08
    Act Density 0.047%

    No Known Activations