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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    .feature
    -0.08
    สวยงาม
    -0.07
     meer
    -0.07
     considered
    -0.07
    uire
    -0.07
     against
    -0.07
    Unique
    -0.07
     bore
    -0.06
    든
    -0.06
    二氧化碳
    -0.06
    POSITIVE LOGITS
    🌏
    0.07
    崚
    0.07
    赤
    0.07
     Telegram
    0.06
    oki
    0.06
    ﰘ
    0.06
     종
    0.06
    มงคล
    0.06
    糌
    0.06
    敕
    0.06
    Act Density 0.052%

    No Known Activations