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

    Neuronpedia

    INDEX
    Explanations

    Table shifting consistency interaction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    0.49
     ecologists
    0.44
     help
    0.43
     helped
    0.43
     wooded
    0.42
     forested
    0.41
     gastroenter
    0.41
     shepherds
    0.41
    有助于
    0.41
    ta
    0.40
    POSITIVE LOGITS
    ال
    0.44
    મો
    0.43
     Türkçe
    0.41
     الثانية
    0.41
     Retro
    0.41
    當時
    0.40
     internationaux
    0.40
    ப்பு
    0.40
     meines
    0.40
    Registration
    0.39
    Act Density 0.009%

    No Known Activations