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

    Neuronpedia

    INDEX
    Explanations

    the article

    np_acts-logits-general · gemini-2.5-flash-lite

    what follows "the"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     受
    0.76
     對
    0.75
     variété
    0.74
    ában
    0.72
     مكان
    0.71
     પછી
    0.71
     者
    0.71
     ലെ
    0.71
     沒有
    0.71
     鞋
    0.70
    POSITIVE LOGITS
    t
    0.79
    т
    0.75
    И
    0.75
    ท
    0.74
    ב
    0.64
    ۔
    0.64
    ی
    0.63
    ת
    0.63
    O
    0.62
    ö
    0.62
    Act Density 0.056%

    No Known Activations