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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ти
    0.83
    t
    0.82
    LEMN
    0.80
    ле
    0.79
    يلي
    0.76
    Task
    0.74
    ₲
    0.73
    algebras
    0.72
     manly
    0.70
    iteten
    0.70
    POSITIVE LOGITS
     pejabat
    0.79
     blij
    0.78
    恤
    0.77
    ދު
    0.77
    捎
    0.76
    ുവെ
    0.75
    北京
    0.74
     ayrıca
    0.73
     отличаются
    0.73
     immobilier
    0.72
    Act Density 0.000%

    No Known Activations