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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    表态
    -0.07
    介质
    -0.07
    的质量
    -0.07
     Sherman
    -0.07
     tung
    -0.07
     deepcopy
    -0.07
    代替
    -0.07
    ٹ
    -0.07
    ducers
    -0.06
    שמר
    -0.06
    POSITIVE LOGITS
    gay
    0.07
    蜻
    0.07
    terms
    0.07
    _NEED
    0.07
    orative
    0.06
     horrific
    0.06
    incl
    0.06
    saving
    0.06
    _conf
    0.06
    \[
    0.06
    Act Density 0.106%

    No Known Activations