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

    Neuronpedia

    INDEX
    Explanations

    Document

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Rates
    -0.06
     نب
    -0.06
     ("<
    -0.06
     boasts
    -0.06
    ATEGY
    -0.06
     |\
    -0.06
    分别
    -0.05
     '/../
    -0.05
     byly
    -0.05
     Ray
    -0.05
    POSITIVE LOGITS
     conexion
    0.07
    .selector
    0.07
     collaboration
    0.07
     durable
    0.07
    Sortable
    0.06
    (coords
    0.06
    (Material
    0.06
     případě
    0.06
    imming
    0.06
     Deputy
    0.06
    Act Density 0.004%

    No Known Activations