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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     mixin
    -0.08
     crust
    -0.07
     interest
    -0.07
    rients
    -0.07
     Ud
    -0.07
     hun
    -0.07
     foyer
    -0.06
     buggy
    -0.06
    aviest
    -0.06
     complement
    -0.06
    POSITIVE LOGITS
    デザイン
    0.08
    ◜
    0.08
    enkins
    0.07
    节水
    0.07
    ◕
    0.07
    🖱
    0.07
    ▣
    0.07
    ㄲ
    0.06
     artır
    0.06
    今まで
    0.06
    Act Density 0.013%

    No Known Activations