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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ramework
    0.55
    iche
    0.51
     フレーム
    0.51
     형태
    0.49
     امریک
    0.49
     について
    0.49
     병
    0.49
    formal
    0.48
     ue
    0.48
     軽量
    0.48
    POSITIVE LOGITS
    ת
    0.57
    то
    0.56
    ت
    0.54
    ل
    0.54
     to
    0.51
    لای
    0.50
    মা
    0.48
    োলার
    0.47
    óstico
    0.47
    תה
    0.46
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.