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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Americans
    -0.07
     araç
    -0.07
     השי
    -0.07
     kể
    -0.07
    UX
    -0.07
    랰
    -0.07
     comps
    -0.06
     dhe
    -0.06
     Cottage
    -0.06
     entrar
    -0.06
    POSITIVE LOGITS
    统治
    0.08
     propagate
    0.08
    编号
    0.07
     sixth
    0.07
    体系建设
    0.07
    免疫
    0.07
     السلام
    0.07
    =[↵
    0.07
     ولم
    0.07
    _approved
    0.07
    Act Density 0.132%

    No Known Activations