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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     paroles
    0.50
    laughs
    0.49
     continuamente
    0.47
     parallèles
    0.46
     Traditions
    0.46
    󰡕
    0.46
     tradiciones
    0.46
     agricoles
    0.44
    イルス
    0.44
    beste
    0.44
    POSITIVE LOGITS
    ه‌ی
    0.47
     surrender
    0.46
     ONLY
    0.45
     only
    0.45
     duty
    0.44
     layman
    0.43
    ින්
    0.43
    ை
    0.42
     an
    0.41
    жу
    0.41
    Act Density 0.015%

    No Known Activations