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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    不断发展
    -0.08
    szę
    -0.08
    שי
    -0.08
    nts
    -0.07
    小伙伴
    -0.07
    ột
    -0.07
    باشر
    -0.07
    ntp
    -0.07
    ץ
    -0.07
    积极作用
    -0.07
    POSITIVE LOGITS
    幛
    0.07
     accusation
    0.07
     submarine
    0.07
    \Traits
    0.07
    -pressure
    0.07
    �
    0.07
    _visibility
    0.06
     FIL
    0.06
     комис
    0.06
    -made
    0.06
    Act Density 0.011%

    No Known Activations