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

    Neuronpedia

    INDEX
    Explanations

    country

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ctype
    -0.07
     fancy
    -0.07
     mục
    -0.07
     utiliz
    -0.06
    edList
    -0.06
     alespoň
    -0.06
    つぶ
    -0.06
    руш
    -0.06
    148
    -0.06
     розпов
    -0.06
    POSITIVE LOGITS
     herk
    0.06
     сегодня
    0.06
     Citizenship
    0.06
     deleting
    0.06
    Chicken
    0.06
    -प
    0.06
     Domain
    0.06
    _reward
    0.06
    Alpha
    0.06
    anguages
    0.06
    Act Density 0.104%

    No Known Activations