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

    Neuronpedia

    INDEX
    Explanations

    race

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    antro
    -0.07
    atern
    -0.07
     explanation
    -0.07
     Bonds
    -0.07
     overriding
    -0.06
    enta
    -0.06
    Pane
    -0.06
    Dispatcher
    -0.06
    unds
    -0.06
     snacks
    -0.06
    POSITIVE LOGITS
     उपय
    0.07
    ��
    0.06
     homeless
    0.06
     merkezi
    0.06
    /save
    0.06
     기억
    0.06
    urent
    0.06
    LayoutManager
    0.06
     Ride
    0.06
    ellation
    0.06
    Act Density 0.006%

    No Known Activations