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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    هد
    0.87
    #![
    0.70
    -
    0.68
     menunggu
    0.67
     グラ
    0.67
     khủng
    0.67
     icons
    0.66
    ,
    0.66
    واه
    0.65
     هز
    0.65
    POSITIVE LOGITS
    тся
    0.90
    ো
    0.89
    𝐚
    0.82
    contrar
    0.81
    isr
    0.80
    reversed
    0.79
    ியில்
    0.79
    etern
    0.78
    櫒
    0.77
    лся
    0.77
    Act Density 0.001%

    No Known Activations