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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ness
    0.95
    nya
    0.91
     pues
    0.86
    ndown
    0.85
     disappointing
    0.82
    rs
    0.81
    遇到的
    0.81
    strual
    0.81
     disadvant
    0.81
    nde
    0.80
    POSITIVE LOGITS
     Christina
    0.95
     तार
    0.93
    カラ
    0.90
     Định
    0.88
    paragraphs
    0.88
    ים
    0.85
    Christina
    0.84
    ടിയ
    0.84
     Shirley
    0.83
    য়ে
    0.83
    Act Density 0.000%

    No Known Activations