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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    kür
    -0.08
    auen
    -0.07
    prepared
    -0.07
     lanz
    -0.07
     InetAddress
    -0.07
    سلح
    -0.07
     spaceship
    -0.07
    牺
    -0.07
    引越し
    -0.07
    iphone
    -0.07
    POSITIVE LOGITS
    ;color
    0.08
    양
    0.07
    的原则
    0.07
    .Entity
    0.07
     probability
    0.07
    比例
    0.07
    uur
    0.07
     precinct
    0.06
    بر
    0.06
     discrimination
    0.06
    Act Density 0.002%

    No Known Activations