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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    rots
    -0.08
     Fre
    -0.07
     exploding
    -0.07
    entially
    -0.07
    .destination
    -0.07
     beneath
    -0.07
    probably
    -0.06
    levels
    -0.06
     skb
    -0.06
    vid
    -0.06
    POSITIVE LOGITS
    商業
    0.07
     마지
    0.07
    避孕
    0.07
    깽
    0.07
     Boxes
    0.07
    ورو
    0.07
    Interval
    0.07
    EventManager
    0.06
     завод
    0.06
    师范
    0.06
    Act Density 0.013%

    No Known Activations