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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Nile
    0.49
     Egyptians
    0.44
     스트
    0.42
     Egyptian
    0.41
     whom
    0.41
     Gener
    0.40
     tubs
    0.39
     HBO
    0.39
    getColumn
    0.39
    whom
    0.39
    POSITIVE LOGITS
    가지
    0.44
     খানের
    0.37
    残
    0.36
    सेच
    0.35
     মুল
    0.35
     نبی
    0.35
    ړ
    0.35
    သိ
    0.35
     buoni
    0.34
    бу
    0.34
    Act Density 0.004%

    No Known Activations