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

    Neuronpedia

    INDEX
    Explanations

    tailor more information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    er
    1.91
    र
    1.52
    ر
    1.46
    is
    1.32
    k
    1.32
    ος
    1.29
    es
    1.28
    pok
    1.28
    mm
    1.27
    ga
    1.26
    POSITIVE LOGITS
     Zudem
    1.75
     shouldUse
    1.59
    ᆭ
    1.57
     hinzu
    1.49
     温度
    1.48
     Dazu
    1.47
    де
    1.46
     இந்ந
    1.43
    щее
    1.41
    ຜະລິດຕ
    1.39
    Act Density 0.103%

    No Known Activations