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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    𝙸
    0.48
    ैक्ट
    0.45
    𝙄
    0.45
    ктак
    0.44
     trifle
    0.44
     রায়
    0.43
     їх
    0.43
     बम
    0.43
     yakin
    0.42
    ᅱ
    0.42
    POSITIVE LOGITS
    ش
    0.54
     (\
    0.48
    前
    0.48
    is
    0.46
     Prince
    0.46
    '$
    0.46
     should
    0.45
     AP
    0.44
    $'
    0.44
     were
    0.43
    Act Density 0.006%

    No Known Activations