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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Kuala
    -0.08
     petite
    -0.08
    genden
    -0.07
    Dig
    -0.07
     heapq
    -0.07
    ICAL
    -0.06
    dh
    -0.06
    acen
    -0.06
    讨厌
    -0.06
     ngờ
    -0.06
    POSITIVE LOGITS
    聲
    0.08
    _ver
    0.07
    楪
    0.07
     UINT
    0.07
    贡献力量
    0.07
    (statement
    0.07
    _ord
    0.07
    zeit
    0.07
    _Metadata
    0.07
    золот
    0.07
    Act Density 0.001%

    No Known Activations