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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Their
    0.71
    他们的
    0.66
     People
    0.61
     Psychology
    0.60
    彭
    0.60
     Пе
    0.59
     Peoples
    0.59
    㺫
    0.59
    GetMapping
    0.59
    вай
    0.59
    POSITIVE LOGITS
     cláss
    0.81
     classique
    0.75
     versão
    0.73
     enlace
    0.73
     rápido
    0.70
     propósito
    0.65
    ান্ত্রিক
    0.65
     supersede
    0.64
     também
    0.64
     artículo
    0.64
    Act Density 0.000%

    No Known Activations