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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    эффици
    0.88
    },\\
    0.88
     sít
    0.84
    oría
    0.82
    ዔ
    0.82
     unidirectional
    0.82
     года
    0.80
    ংস
    0.80
    циями
    0.80
     powert
    0.79
    POSITIVE LOGITS
    ب
    0.84
     sauf
    0.80
     dessin
    0.79
    實際
    0.77
     locaux
    0.76
     deux
    0.75
     faire
    0.75
    four
    0.75
    e
    0.74
    實際上
    0.73
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.