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

    Neuronpedia

    INDEX
    Explanations

    numeric strings inside text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0
    0.29
    5
    0.28
    -=
    0.25
    4
    0.24
    7
    0.23
    bb
    0.23
    Day
    0.23
    GONE
    0.22
    9
    0.22
     night
    0.22
    POSITIVE LOGITS
    itabbam
    0.26
    쿰
    0.25
    垁
    0.24
    غذ
    0.24
     quím
    0.24
    واب
    0.23
    テム
    0.23
    вак
    0.23
    訲
    0.23
     ऑर्डर
    0.23
    Act Density 0.041%

    No Known Activations