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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Э
    0.97
    ты
    0.94
    𝐱
    0.88
    ры
    0.88
    нибудь
    0.86
    ía
    0.84
     Только
    0.83
    ён
    0.82
     observaciones
    0.82
     Мы
    0.82
    POSITIVE LOGITS
    簧
    0.72
    transformer
    0.72
    Page
    0.71
    immune
    0.69
    Cedar
    0.68
    protection
    0.68
    ات
    0.66
    TEL
    0.65
    bone
    0.64
    міністра
    0.64
    Act Density 0.000%

    No Known Activations