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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Remark
    0.83
    resulting
    0.80
     resulting
    0.78
     jangka
    0.78
    การ
    0.77
     expansive
    0.76
    inducing
    0.76
    $[\
    0.75
    expanding
    0.75
    typical
    0.74
    POSITIVE LOGITS
     Francis
    0.92
     Dorset
    0.89
     francis
    0.83
    海拔
    0.82
     José
    0.81
     fiancée
    0.79
    itschrift
    0.79
     англий
    0.78
     Tree
    0.77
     girlfriend
    0.77
    Act Density 0.000%

    No Known Activations