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

    Neuronpedia

    INDEX
    Explanations

    labels followed by colon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    岄
    0.44
    ссию
    0.42
     magari
    0.38
    kových
    0.38
    必要的
    0.36
    湁
    0.35
    !",
    0.35
    화를
    0.35
    LocalDate
    0.34
    ખ
    0.34
    POSITIVE LOGITS
    ：
    0.57
    :
    0.57
    ?:
    0.54
     approx
    0.53
     :
    0.50
    ?
    0.48
    :"
    0.48
     Approx
    0.48
    ：“
    0.47
     매우
    0.47
    Act Density 0.073%

    No Known Activations