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

    Neuronpedia

    INDEX
    Explanations

    ogeneity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <Transaction
    -0.08
    Metal
    -0.07
     maxx
    -0.07
    controlled
    -0.07
     Delicious
    -0.07
    (Module
    -0.07
    中共中央
    -0.07
    鱼类
    -0.07
    ’en
    -0.07
     relative
    -0.06
    POSITIVE LOGITS
    ╉
    0.07
    []{↵
    0.07
    peration
    0.07
    卡通
    0.07
     конкрет
    0.07
    angepicker
    0.07
    WARN
    0.06
     Lazar
    0.06
     Wordpress
    0.06
     Backpack
    0.06
    Act Density 0.002%

    No Known Activations