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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     your
    0.56
    your
    0.48
     आपका
    0.43
    你的
    0.43
    يت
    0.43
    드
    0.42
    꼬
    0.42
    entretien
    0.41
    0.41
     votre
    0.40
    POSITIVE LOGITS
     выпущен
    0.50
     допол
    0.47
    導演
    0.46
     फैलाने
    0.46
     החד
    0.46
    Reform
    0.45
    新たに
    0.45
     dintre
    0.45
     جیتنے
    0.44
     घोषणा
    0.44
    Act Density 0.001%

    No Known Activations