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

    Neuronpedia

    INDEX
    Explanations

    Training and development

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     theorists
    -0.07
    _testing
    -0.06
    奥
    -0.06
    -base
    -0.06
     двиг
    -0.06
     ",
↵
    -0.06
    Fn
    -0.06
    ادات
    -0.06
    -schema
    -0.06
    ίθ
    -0.06
    POSITIVE LOGITS
    .getDate
    0.08
     وغير
    0.07
     Manus
    0.06
    опол
    0.06
    トル
    0.06
    군
    0.06
     perceived
    0.06
     homophobic
    0.06
    .InnerText
    0.06
    うん
    0.06
    Act Density 0.042%

    No Known Activations