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

    Neuronpedia

    INDEX
    Explanations

    proving or proofreading

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ᆢ
    2.03
    preneurs
    1.94
     Außerdem
    1.77
     Еще
    1.73
    裡的
    1.73
    чил
    1.71
    淳
    1.68
    麼
    1.67
    anfaatkan
    1.63
    <0x80>
    1.61
    POSITIVE LOGITS
    ح
    2.41
    га
    2.31
    ни
    2.19
    ﻤ
    1.97
    ون
    1.85
    кс
    1.85
    क
    1.82
     déjà
    1.78
     substantiate
    1.77
    이지
    1.75
    Act Density 0.027%

    No Known Activations