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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    DropDownStyle
    1.36
     jewel
    1.35
     ưa
    1.30
     linearized
    1.29
    구요
    1.29
     flare
    1.27
    fullname
    1.23
    ございます
    1.23
     Militia
    1.21
     helpless
    1.21
    POSITIVE LOGITS
    तील
    1.22
    دي
    1.14
    l
    1.12
    M
    1.10
    o
    1.10
    am
    1.08
    ελ
    1.07
     pux
    1.07
    स्कृतिक
    1.06
    e
    1.06
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.