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

    Neuronpedia

    INDEX
    Explanations

    red

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ，说
    -0.07
     PROPERTY
    -0.07
     Monk
    -0.07
     parlament
    -0.07
     çab
    -0.07
     Mood
    -0.06
    	aux
    -0.06
    ourt
    -0.06
    observer
    -0.06
    BarController
    -0.06
    POSITIVE LOGITS
     мереж
    0.10
     redes
    0.08
     Network
    0.08
     réseau
    0.07
     network
    0.07
    Network
    0.07
    Net
    0.07
     networks
    0.07
     Rede
    0.07
     리
    0.06
    Act Density 0.007%

    No Known Activations