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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Vegetable
    -0.07
     систем
    -0.07
    -variable
    -0.06
     credited
    -0.06
     velký
    -0.06
     dr
    -0.06
    енное
    -0.06
     reopened
    -0.06
    lices
    -0.06
    يع
    -0.06
    POSITIVE LOGITS
    इसक
    0.06
    (Application
    0.06
     colonial
    0.06
    	cuda
    0.06
     pensions
    0.06
    @WebServlet
    0.06
    ’a
    0.06
    :@{
    0.06
    'a
    0.06
     trolling
    0.06
    Act Density 0.001%

    No Known Activations