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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    v
    0.50
     Twp
    0.48
    g
    0.46
     Gao
    0.44
    嗳
    0.42
    ga
    0.41
    UInt
    0.41
    шель
    0.41
     had
    0.41
     Hạ
    0.41
    POSITIVE LOGITS
     atend
    0.52
    鐵
    0.50
    民間
    0.45
    𝓈
    0.44
     மக்களின்
    0.44
    हमारे
    0.44
    斬
    0.43
    หน
    0.43
    nable
    0.43
    rocyte
    0.43
    Act Density 0.001%

    No Known Activations