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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    e
    0.83
    ть
    0.80
    वे
    0.76
     \)
    0.74
    ers
    0.74
     первые
    0.73
    2
    0.73
     দিন
    0.72
    ция
    0.71
    FFER
    0.69
    POSITIVE LOGITS
    निम्नलिखित
    0.70
    🕉
    0.69
    کور
    0.67
    زی
    0.66
    രോധ
    0.66
    此类
    0.66
    热爱
    0.65
     मुकेश
    0.64
    çük
    0.64
    横浜
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.