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

    Neuronpedia

    INDEX
    Explanations

    various formatting elements and diverse content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    to
    0.53
    t
    0.52
    the
    0.49
     (
    0.48
     cross
    0.48
    (
    0.46
     key
    0.45
    #
    0.45
    Part
    0.45
    f
    0.45
    POSITIVE LOGITS
     decisões
    0.51
    StructOf
    0.48
     ሰዎች
    0.46
     获取
    0.46
    的感觉
    0.45
    💨
    0.45
     自分
    0.45
    າ
    0.45
    pOt
    0.44
    ါ
    0.44
    Act Density 0.017%

    No Known Activations