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

    Neuronpedia

    INDEX
    Explanations

    a lot of people and things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ۔
    0.35
     posibil
    0.34
     bitte
    0.31
     シ
    0.30
     außerdem
    0.30
     ذریع
    0.30
     possíveis
    0.30
    》，
    0.30
     هاي
    0.30
     varied
    0.29
    POSITIVE LOGITS
    人都
    0.58
     have
    0.43
     имеют
    0.42
    人は
    0.42
    oretically
    0.41
     are
    0.41
     companies
    0.41
     έχουν
    0.38
     άνθρω
    0.38
    都有
    0.38
    Act Density 0.057%

    No Known Activations