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

    Neuronpedia

    INDEX
    Explanations

    dl

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     svm
    -0.07
    也是一个
    -0.07
    米尔
    -0.07
     viewModel
    -0.07
     lum
    -0.07
    vx
    -0.07
    common
    -0.07
    Eat
    -0.07
     remorse
    -0.07
    -row
    -0.06
    POSITIVE LOGITS
    	RTLR
    0.07
    작
    0.07
     chống
    0.07
    فحص
    0.07
     bağlant
    0.06
    請
    0.06
    مواد
    0.06
    href
    0.06
     Lịch
    0.06
    には
    0.06
    Act Density 0.010%

    No Known Activations