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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    college
    -0.07
    栟
    -0.07
    شدد
    -0.07
     Wake
    -0.06
    ᴛ
    -0.06
     quantitative
    -0.06
     chù
    -0.06
     onComplete
    -0.06
     concentrating
    -0.06
    过关
    -0.06
    POSITIVE LOGITS
    芳香
    0.07
    ↵↵
    0.07
     incarcer
    0.07
    𝙽
    0.07
    𝑺
    0.07
    许多人
    0.06
    subscriber
    0.06
    又要
    0.06
    �
    0.06
    供
    0.06
    Act Density 0.251%

    No Known Activations