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

    Neuronpedia

    INDEX
    Explanations

    HTML tags and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <0x80>
    1.02
    ﻦ
    0.98
    TimeControl
    0.89
     براي
    0.88
     lâm
    0.87
    ých
    0.86
    ﮯ
    0.86
     zijn
    0.86
    вная
    0.86
    වේ
    0.86
    POSITIVE LOGITS
    a
    1.72
    ה
    1.25
    ه
    1.23
    1
    1.14
    ા
    1.04
    ون
    0.98
    aided
    0.98
    an
    0.97
    ب
    0.97
    fueled
    0.91
    Act Density 0.000%

    No Known Activations