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

    Neuronpedia

    INDEX
    Explanations

    ob

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    101
    -0.07
    Soph
    -0.07
    Dual
    -0.07
    Produ
    -0.06
     aque
    -0.06
    curities
    -0.06
     Hou
    -0.06
    qw
    -0.06
    Keys
    -0.06
    _\
    -0.06
    POSITIVE LOGITS
    AppBundle
    0.08
     Jakarta
    0.07
    ################################
    0.07
     ﺍ
    0.07
    وات
    0.06
    項
    0.06
     wrestling
    0.06
     relatives
    0.06
    none
    0.06
     Fortnite
    0.06
    Act Density 0.004%

    No Known Activations