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

    Neuronpedia

    INDEX
    Explanations

    as well as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    萂
    0.48
    的三
    0.46
     அறிவி
    0.43
     sello
    0.43
    蕌
    0.42
     tokom
    0.41
    <unused35>
    0.41
    엮
    0.41
     dépl
    0.39
    âme
    0.39
    POSITIVE LOGITS
    一个
    0.43
    ester
    0.43
    ߋ
    0.42
    ה
    0.40
     your
    0.40
     or
    0.39
    Er
    0.39
     Gambling
    0.39
     oder
    0.38
    ց
    0.38
    Act Density 0.003%

    No Known Activations