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

    Neuronpedia

    INDEX
    Explanations

    App

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
    時点
    -0.07
    ｻ
    -0.07
     nave
    -0.07
    _Params
    -0.07
    �
    -0.06
    submenu
    -0.06
     purch
    -0.06
    .quant
    -0.06
     discrepan
    -0.06
    POSITIVE LOGITS
     квартир
    0.08
    文化艺术
    0.07
     circumstances
    0.07
     Forex
    0.07
    文学
    0.07
     Views
    0.07
     الثلاثاء
    0.07
    _bal
    0.07
    .Butter
    0.07
     WOW
    0.07
    Act Density 0.004%

    No Known Activations