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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Questo
    0.64
     นี่
    0.58
    Pero
    0.57
    Đây
    0.57
    Finalmente
    0.57
    Prova
    0.57
    Explanation
    0.57
    Cadastro
    0.56
    Lista
    0.55
    Dieser
    0.55
    POSITIVE LOGITS
     depending
    0.63
     bergantung
    0.61
     depend
    0.60
     tergantung
    0.59
     depende
    0.59
     depends
    0.59
     optionally
    0.54
    取决于
    0.54
     predomin
    0.54
     ideally
    0.54
    Act Density 0.467%

    No Known Activations