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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    G
    0.72
     Relation
    0.71
     Kat
    0.68
    ۓ
    0.67
     بنائیں
    0.65
     Publications
    0.64
     dirigés
    0.64
    O
    0.64
     Compt
    0.63
     JP
    0.62
    POSITIVE LOGITS
    érieure
    0.75
    <unused2221>
    0.68
     punched
    0.66
    uously
    0.64
    rhein
    0.64
     benefited
    0.62
    ziert
    0.62
    geek
    0.62
    🥫
    0.61
    ungkinan
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.