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

    Neuronpedia

    INDEX
    Explanations

    guides and documentation for users

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     offizi
    0.49
    页面
    0.49
     written
    0.48
    instructions
    0.45
     resmi
    0.45
     официа
    0.44
     문서
    0.44
     écrit
    0.44
    ページ
    0.44
     sayfası
    0.44
    POSITIVE LOGITS
     user
    0.53
    ユーザ
    0.51
     operator
    0.47
     administrator
    0.47
     usuarios
    0.46
     пользователь
    0.45
     użytk
    0.45
     utilisateur
    0.45
    user
    0.44
     User
    0.42
    Act Density 0.009%

    No Known Activations