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

    Neuronpedia

    INDEX
    Explanations

    expressions of welcome and happiness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﺖ
    1.52
     proposent
    1.45
     стоимости
    1.33
    oqu
    1.32
     utilisées
    1.30
    يز
    1.29
    <!--
    1.27
    দ্র
    1.27
    ebe
    1.27
    ak
    1.26
    POSITIVE LOGITS
    ani
    1.48
    もあり
    1.45
    시킨
    1.40
    с
    1.35
    不愿意
    1.34
    ных
    1.28
    ский
    1.28
    ス
    1.27
     społecz
    1.26
    ened
    1.23
    Act Density 0.154%

    No Known Activations