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

    Neuronpedia

    INDEX
    Explanations

    enlist and enlistments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    i
    1.35
    ET
    1.33
    il
    1.30
    sville
    1.27
    n
    1.20
    es
    1.19
    ne
    1.17
     sexes
    1.17
     Тут
    1.16
    et
    1.15
    POSITIVE LOGITS
    ч
    1.83
    ע
    1.64
    а
    1.58
    いた
    1.50
    ло
    1.39
    ном
    1.37
    щ
    1.36
    ни
    1.32
    го
    1.31
    от
    1.31
    Act Density 0.000%

    No Known Activations