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

    Neuronpedia

    INDEX
    Explanations

    thin membrane

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ا
    2.34
    ї
    2.27
    ла
    2.08
    ılarak
    2.03
    ból
    2.02
    ش
    2.02
    ้
    2.02
    钅
    1.98
    ျေး
    1.94
    ções
    1.88
    POSITIVE LOGITS
     debunk
    1.90
     easter
    1.72
     Pets
    1.71
    suits
    1.69
     Professions
    1.63
     refundable
    1.60
     fluv
    1.57
    PED
    1.56
    ب
    1.56
    隍
    1.56
    Act Density 0.245%

    No Known Activations