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

    Neuronpedia

    INDEX
    Explanations

    mapping coordinates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ο
    0.45
    BC
    0.43
    re
    0.43
    ابقة
    0.43
    arrière
    0.42
    эт
    0.42
    Cómo
    0.41
     modelo
    0.40
    Мы
    0.40
    unker
    0.39
    POSITIVE LOGITS
     ARTICLE
    0.47
     ಕ್ರಮ
    0.47
    變化
    0.45
     Motions
    0.44
     descend
    0.43
     Citizenship
    0.43
     പങ്കെടു
    0.43
     nell
    0.42
     istnieje
    0.41
    ള്
    0.41
    Act Density 0.011%

    No Known Activations