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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    现存
    -0.08
    óng
    -0.08
    CastException
    -0.07
     Extr
    -0.06
     combust
    -0.06
    Resistance
    -0.06
    摇滚
    -0.06
    Esp
    -0.06
    能在
    -0.06
    的确是
    -0.06
    POSITIVE LOGITS
     başlayan
    0.07
     human
    0.07
    ncpy
    0.07
     Spa
    0.06
    WHO
    0.06
    nię
    0.06
    -au
    0.06
    連れ
    0.06
    本科生
    0.06
     Vera
    0.06
    Act Density 0.002%

    No Known Activations