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

    Neuronpedia

    INDEX
    Explanations

    so

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /layouts
    -0.07
    DG
    -0.07
    expenses
    -0.06
    lings
    -0.06
     accommod
    -0.06
     リ
    -0.06
     payouts
    -0.06
     belli
    -0.06
     ـ
    -0.06
    】【
    -0.06
    POSITIVE LOGITS
     oat
    0.07
     ресурс
    0.07
     parent
    0.07
    Louis
    0.06
    Break
    0.06
     billeder
    0.06
     Maple
    0.06
     odak
    0.06
    _GenericClass
    0.06
    ат
    0.06
    Act Density 0.001%

    No Known Activations