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

    Neuronpedia

    INDEX
    Explanations

    after

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     uniqu
    -0.07
    .getStyle
    -0.07
     bas
    -0.06
    اسه
    -0.06
    .yml
    -0.06
    serializer
    -0.06
    ﾑ
    -0.06
    roperty
    -0.06
     چون
    -0.06
    mk
    -0.06
    POSITIVE LOGITS
     QList
    0.06
    ظيف
    0.06
     cái
    0.06
     =================================================
    0.06
     bouquet
    0.06
    _DIG
    0.06
     cos
    0.06
    PACK
    0.06
     museums
    0.06
     assessment
    0.06
    Act Density 0.209%

    No Known Activations