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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     NSCoder
    -0.07
    渟
    -0.06
    �
    -0.06
     splendid
    -0.06
    �
    -0.06
     טי
    -0.06
    indle
    -0.06
     hugely
    -0.06
     bp
    -0.06
     endorsing
    -0.06
    POSITIVE LOGITS
    angled
    0.08
    的方式来
    0.07
    ация
    0.07
    ÇÃO
    0.07
    ец
    0.07
    特性
    0.06
    冬
    0.06
    关税
    0.06
    .decrypt
    0.06
    ♫
    0.06
    Act Density 0.011%

    No Known Activations