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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     airs
    -0.08
    营养
    -0.07
    فيل
    -0.07
     Umb
    -0.07
    auss
    -0.07
    là
    -0.06
     Applies
    -0.06
     NEVER
    -0.06
    ıs
    -0.06
     Doyle
    -0.06
    POSITIVE LOGITS
     winning
    0.07
     cleaned
    0.07
    ใน
    0.07
    _INS
    0.07
     tabletop
    0.07
     nullable
    0.06
     classroom
    0.06
    stock
    0.06
    _shared
    0.06
    市场
    0.06
    Act Density 0.001%

    No Known Activations