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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     інформа
    0.72
     grape
    0.71
    ה
    0.71
    นาง
    0.70
    น
    0.69
    אים
    0.68
     寝
    0.66
     pomegranate
    0.65
     intestines
    0.65
    ین
    0.64
    POSITIVE LOGITS
    К
    0.83
    🙏
    0.79
    कांड
    0.78
    YOU
    0.77
    싸
    0.77
    ❤️❤️
    0.75
    ‍
    0.75
    ToArray
    0.73
    टी
    0.72
    K
    0.72
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.