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

    Neuronpedia

    INDEX
    Explanations

    sections and their contents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ám
    0.42
    How
    0.41
    ς
    0.41
     streamline
    0.41
     do
    0.41
    但是在
    0.40
    ્લે
    0.40
    MW
    0.40
    Ｌ
    0.39
     στην
    0.39
    POSITIVE LOGITS
    dziel
    0.46
     Fried
    0.45
    सु
    0.43
    ırlar
    0.43
     sauvegard
    0.43
    uximab
    0.42
    थल
    0.42
     থাকছে
    0.42
     inactivació
    0.42
    ır
    0.41
    Act Density 0.001%

    No Known Activations