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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     pulverized
    0.61
     bipolar
    0.60
    垨
    0.59
     polarized
    0.59
     Howell
    0.59
     flanked
    0.59
     deseas
    0.59
     polarizing
    0.57
     heatmap
    0.57
    स्तरीय
    0.57
    POSITIVE LOGITS
    Работа
    0.78
    别人的
    0.75
     услуги
    0.70
     能力
    0.69
     награ
    0.68
     Tätigkeit
    0.68
     tirelessly
    0.66
    每天
    0.66
     tevé
    0.66
    作業
    0.64
    Act Density 0.823%

    No Known Activations