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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    bullying
    0.80
    平板
    0.80
    Escol
    0.74
    firefox
    0.74
    ྥ
    0.74
    اقة
    0.73
    ী
    0.73
    ্স
    0.73
    燾
    0.72
    𐰴
    0.72
    POSITIVE LOGITS
     וב
    0.85
     trở
    0.80
     പ്രവർത്തന
    0.79
    pä
    0.78
    م
    0.77
     subsequently
    0.75
    м
    0.74
     Gó
    0.73
     en
    0.72
     quân
    0.72
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.