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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Then
    -0.08
    ヅ
    -0.07
    的一项
    -0.07
    .month
    -0.07
    重大
    -0.07
    azo
    -0.07
     longer
    -0.07
    诞生
    -0.07
    unlikely
    -0.07
    Background
    -0.07
    POSITIVE LOGITS
     Weapon
    0.09
    <Element
    0.08
    侵略
    0.08
    _http
    0.08
    魉
    0.07
    /model
    0.07
    (Font
    0.07
    subtype
    0.07
    活泼
    0.07
             ↵
    0.07
    Act Density 0.003%

    No Known Activations