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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     suisse
    0.42
     tej
    0.42
     jeudi
    0.42
     remboursement
    0.41
     tiss
    0.40
    sqrt
    0.39
     aidant
    0.39
     taxes
    0.39
    owym
    0.39
    chte
    0.39
    POSITIVE LOGITS
    ไน
    0.41
     Swal
    0.40
    ㅎ
    0.40
    阌
    0.39
    த்தான்
    0.39
    🐉
    0.38
    alada
    0.37
     విధంగా
    0.36
    ான்
    0.36
     시
    0.36
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.