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

    Neuronpedia

    INDEX
    Explanations

    diagnosis format

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ，”
    1.57
     '}';
    1.33
    ってください
    1.31
    Ϫ
    1.30
    。”
    1.28
    。」
    1.28
    ），
    1.28
    "،
    1.24
    ],"
    1.24
    ,'"
    1.23
    POSITIVE LOGITS
     &
    3.27
    &
    2.63
     &/
    2.19
    &-
    1.83
    ＆
    1.69
     &-
    1.67
     &(
    1.64
    )&
    1.59
     &\
    1.56
    &+
    1.56
    Act Density 0.513%

    No Known Activations