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

    Neuronpedia

    INDEX
    Explanations

    doing chores

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Healthcare
    0.44
    łka
    0.44
     অঞ্চল
    0.42
    )",
    0.41
    {}",
    0.40
    swing
    0.40
     Sporting
    0.40
    영
    0.39
    ",
    0.39
     {})
    0.38
    POSITIVE LOGITS
    ította
    0.44
    StudentID
    0.42
     detr
    0.41
     shrinkage
    0.41
    RIB
    0.41
    ｲ
    0.40
    спонд
    0.39
    Ꭱ
    0.39
    いましたが
    0.38
    宿舍
    0.38
    Act Density 0.003%

    No Known Activations