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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     sab
    0.50
    0.48
    IN
    0.46
     ترمیم
    0.43
    ↵↵
    0.43
    IL
    0.41
     Holy
    0.41
     nalazi
    0.41
    ↓
    0.40
    んでも
    0.40
    POSITIVE LOGITS
    ються
    0.57
    шки
    0.46
    শরণ
    0.46
    r
    0.45
    φέρον
    0.45
     Giacomo
    0.45
    ள்
    0.44
     schöne
    0.44
    spolit
    0.44
     Ashken
    0.44
    Act Density 0.003%

    No Known Activations