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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ുകൊണ്ട്
    0.61
    ുകൊണ്ട
    0.51
    かしい
    0.48
     throwIf
    0.48
    それでは
    0.46
     SalesLT
    0.45
    XXXXXXXXXXXXXXXX
    0.45
    용한
    0.45
    不支持
    0.44
    ัติ
    0.44
    POSITIVE LOGITS
     depending
    4.50
     depends
    4.22
    depending
    4.16
     depend
    4.13
     зависит
    3.84
     Depending
    3.81
     depended
    3.80
     depende
    3.80
    Depending
    3.80
    depends
    3.80
    Act Density 1.771%

    No Known Activations