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

    Neuronpedia

    INDEX
    Explanations

    each or every

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     창
    0.45
    lecture
    0.40
    աս
    0.39
     manus
    0.38
     adduced
    0.38
    는
    0.38
    창
    0.38
    blade
    0.38
    于
    0.37
     "'
    0.37
    POSITIVE LOGITS
     mỗi
    0.49
     everytime
    0.45
     ומ
    0.44
    誰
    0.44
     ежеднев
    0.44
     وم
    0.44
     каждым
    0.43
    ারিত
    0.43
     россия
    0.43
     Barriers
    0.42
    Act Density 0.002%

    No Known Activations