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
    答
    -0.07
     suited
    -0.06
    Heat
    -0.06
    ʕ
    -0.06
    itto
    -0.06
    reff
    -0.06
     giờ
    -0.06
     Surre
    -0.06
    效能
    -0.06
     seiner
    -0.06
    POSITIVE LOGITS
    旅游局
    0.07
     المصر
    0.07
     입력
    0.07
     precios
    0.07
     בירושלים
    0.07
    一定的
    0.06
    .timestamp
    0.06
    ivo
    0.06
    ('''
    0.06
     imagen
    0.06
    Act Density 0.001%

    No Known Activations