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

    Neuronpedia

    INDEX
    Explanations

    healthy lifestyle and coping

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    speople
    2.95
    ك
    1.95
    sch
    1.88
    sons
    1.84
    κ
    1.80
    nath
    1.74
    es
    1.73
    schrift
    1.72
    sville
    1.70
    s
    1.69
    POSITIVE LOGITS
    부터
    1.80
    ﻁ
    1.78
    ้
    1.70
    ที่จะ
    1.67
    ﯿ
    1.67
    哿
    1.61
    taining
    1.60
    왤
    1.58
    и
    1.57
    ﺹ
    1.57
    Act Density 0.000%

    No Known Activations