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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Upper
    -0.08
     accompanied
    -0.08
     WELL
    -0.07
    =a
    -0.07
    Apellido
    -0.07
    ToUpper
    -0.07
     hanno
    -0.07
    巢
    -0.07
    Weights
    -0.07
    碨
    -0.07
    POSITIVE LOGITS
    мон
    0.07
    /html
    0.07
     Paths
    0.07
     búsqueda
    0.07
     ingl
    0.07
     Hulk
    0.07
    leness
    0.07
    習
    0.07
    ⏏
    0.06
    返
    0.06
    Act Density 0.056%

    No Known Activations