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

    Neuronpedia

    INDEX
    Explanations

    safe topics/categories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ㄆ
    0.57
    å
    0.54
     dobbiamo
    0.53
     slippers
    0.50
     ಜೀವನ
    0.50
    拡
    0.50
    ܣ
    0.49
     ಮನೆಯ
    0.49
    ⱪ
    0.49
     tendremos
    0.48
    POSITIVE LOGITS
    Response
    0.50
    ArrayBox
    0.49
    Event
    0.43
    Business
    0.42
    用于
    0.42
    in
    0.41
    Mapping
    0.41
    Responses
    0.41
    duced
    0.41
    Cities
    0.40
    Act Density 0.000%

    No Known Activations