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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     डबल
    0.44
     Double
    0.41
    ダブル
    0.39
     DOUBLE
    0.38
     dailySales
    0.36
     acts
    0.36
    Double
    0.36
     ប
    0.36
    ర్చు
    0.36
    <unused38>
    0.35
    POSITIVE LOGITS
    uly
    0.42
     Vallée
    0.39
     Zb
    0.39
    yz
    0.38
    Aire
    0.38
    origins
    0.38
     Origins
    0.37
    lação
    0.37
    ushu
    0.37
    Origins
    0.37
    Act Density 0.000%

    No Known Activations