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

    Neuronpedia

    INDEX
    Explanations

    arrow function callbacks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ing
    1.27
    ur
    1.04
    ee
    1.00
    ر
    0.99
     for
    0.96
    ם
    0.96
    it
    0.94
    ן
    0.94
    ли
    0.93
    meler
    0.91
    POSITIVE LOGITS
    ların
    0.91
    (()
    0.89
    ها
    0.84
     clínicos
    0.80
    时间
    0.78
    Bookmarks
    0.75
    That
    0.74
    ':'
    0.72
    𝙀
    0.72
    情况
    0.71
    Act Density 0.002%

    No Known Activations