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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     -
    0.46
     for
    0.44
     (
    0.43
     its
    0.42
     as
    0.42
     linkages
    0.42
    ³
    0.41
     he
    0.40
     yields
    0.40
     or
    0.39
    POSITIVE LOGITS
     乀
    0.61
     Сасик
    0.56
    Someone
    0.55
     あなた
    0.55
    Usuario
    0.54
    purecounter
    0.54
    あなたの
    0.54
    Você
    0.53
    ARCHIVO
    0.52
     kleines
    0.52
    Act Density 0.000%

    No Known Activations