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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ný
    0.57
    niveau
    0.52
     مدير
    0.51
     كيف
    0.50
    ológicas
    0.50
    ló
    0.50
     якому
    0.50
    gewicht
    0.49
    사가
    0.48
     γε
    0.48
    POSITIVE LOGITS
     a
    0.53
     W
    0.49
     LGBTQ
    0.49
     RAM
    0.47
     Macy
    0.46
     MEX
    0.46
     x
    0.45
     X
    0.44
     NFT
    0.44
     CBD
    0.44
    Act Density 0.000%

    No Known Activations