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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     детей
    -0.07
    imp
    -0.07
    embers
    -0.06
     контра
    -0.06
     luật
    -0.06
     chua
    -0.06
     eru
    -0.06
     vendors
    -0.06
     people
    -0.06
     rates
    -0.06
    POSITIVE LOGITS
    Это
    0.06
    gte
    0.06
     Это
    0.06
    uary
    0.06
    .axes
    0.06
    ONGL
    0.06
    <ID
    0.06
    Convert
    0.06
    ocument
    0.06
    485
    0.06
    Act Density 0.003%

    No Known Activations