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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    匱
    0.50
     እንቅ
    0.50
     spermat
    0.50
     oversaw
    0.48
     refuted
    0.48
    ፕሮ
    0.47
     mayam
    0.47
     הבי
    0.46
     STRU
    0.45
    スペ
    0.45
    POSITIVE LOGITS
    ar
    0.56
    ap
    0.56
    api
    0.54
    aw
    0.50
    h
    0.49
    ag
    0.48
    ig
    0.48
    ang
    0.47
    apin
    0.47
    arga
    0.47
    Act Density 0.000%

    No Known Activations