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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    س
    1.17
    𝘢
    1.16
    𝘷
    1.14
    য়
    1.09
    स
    1.08
    𝘳
    1.06
    𝚣
    1.04
    𝘨
    0.97
    ***********
    0.97
    ratulations
    0.96
    POSITIVE LOGITS
    பு
    0.94
    ඥ
    0.92
     denominator
    0.92
     दलों
    0.92
     afferm
    0.92
    ك
    0.91
    ત્મક
    0.89
    НИЕ
    0.89
    buro
    0.88
     correctness
    0.86
    Act Density 0.097%

    No Known Activations