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

    Neuronpedia

    INDEX
    Explanations

    introduce yourself or your drive

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -
    1.30
    ée
    1.27
    anza
    1.16
    '
    1.13
    aire
    1.10
    ل
    1.07
    cular
    1.06
    인
    1.05
    ما
    1.03
    omer
    1.02
    POSITIVE LOGITS
    ﻛ
    1.48
     Ша
    1.32
    ورسٹی
    1.29
     Ihnen
    1.25
     numerosos
    1.23
    ﻧ
    1.21
    ARCHIVO
    1.20
     Володи
    1.20
     plunder
    1.20
    IMAGES
    1.19
    Act Density 0.000%

    No Known Activations