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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    (lhs
    -0.07
     духов
    -0.07
    忻
    -0.07
     substant
    -0.07
     fourn
    -0.06
     contender
    -0.06
    [msg
    -0.06
    кров
    -0.06
    叩
    -0.06
    Friend
    -0.06
    POSITIVE LOGITS
    _penalty
    0.08
    ategorias
    0.07
     प
    0.07
    走过
    0.07
    ancers
    0.07
    สบาย
    0.07
     cruising
    0.07
     نقاط
    0.07
     stalking
    0.06
    门户网站
    0.06
    Act Density 0.000%

    No Known Activations