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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     japanese
    -0.07
     favourites
    -0.07
    𝓋
    -0.07
    prof
    -0.07
    trand
    -0.07
     privé
    -0.07
    :int
    -0.06
    FAST
    -0.06
    贵金属
    -0.06
    ₎
    -0.06
    POSITIVE LOGITS
    必要
    0.07
     dictates
    0.07
    门口
    0.07
    叙事
    0.07
     summarizes
    0.07
     الولا
    0.07
    科技进步
    0.07
    帚
    0.07
     squarely
    0.07
    �
    0.07
    Act Density 0.033%

    No Known Activations