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

    Neuronpedia

    INDEX
    Explanations

    offers help or specific dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Society
    0.49
     ples
    0.47
     pls
    0.46
    Binary
    0.46
    riu
    0.45
    lak
    0.45
    wish
    0.45
     นี้
    0.45
     Society
    0.45
     ло
    0.44
    POSITIVE LOGITS
     iterating
    0.45
     aeration
    0.43
    ربعة
    0.43
     Bezug
    0.43
     electrode
    0.42
    اسم
    0.42
     monadic
    0.42
     catheters
    0.41
     Unters
    0.41
    DataAnnotations
    0.40
    Act Density 0.002%

    No Known Activations