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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     कृति
    0.79
    ционный
    0.77
     ಆಗಿದೆ
    0.75
    товой
    0.74
     दरवाजा
    0.73
     आंकड़ा
    0.72
    igsaw
    0.72
     bebida
    0.71
    ⊷
    0.71
    有一定的
    0.70
    POSITIVE LOGITS
    s
    1.45
    swith
    1.27
    们
    1.27
    們
    1.24
    es
    1.22
    sthe
    1.18
    ים
    1.16
    𝘀
    1.10
    ्स
    1.05
    larla
    1.04
    Act Density 0.975%

    No Known Activations