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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    liness
    1.57
    ্পনিক
    1.34
    ：
    1.32
    ،
    1.27
     Charm
    1.21
     sprawl
    1.19
    াকাছি
    1.18
     Palaiseau
    1.18
     seguros
    1.18
     equivari
    1.17
    POSITIVE LOGITS
    s
    1.71
    ्स
    1.57
    ों
    1.54
    া
    1.48
    ా
    1.48
    ের
    1.45
    ać
    1.44
    ੀ
    1.42
    ς
    1.40
    ał
    1.39
    Act Density 0.031%

    No Known Activations