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

    Neuronpedia

    INDEX
    Explanations

    TODO comments followed by titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    هم
    2.12
    न
    2.06
    ோ
    1.88
    ت
    1.73
    с
    1.63
    た
    1.62
     TODO
    1.61
    l
    1.61
    ed
    1.57
    на
    1.54
    POSITIVE LOGITS
    ς
    1.94
    DING
    1.83
     corpora
    1.82
    ../../
    1.76
    lems
    1.75
    🏻
    1.74
    sib
    1.72
    办法
    1.69
    Ȧ
    1.69
     AppBsky
    1.69
    Act Density 0.002%

    No Known Activations