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

    Neuronpedia

    INDEX
    Explanations

    Program

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    onomies
    -0.07
    Directions
    -0.07
     rá
    -0.07
    (ms
    -0.06
     secretary
    -0.06
    みな
    -0.06
    導
    -0.06
    喪
    -0.06
    ⬇
    -0.06
    墨
    -0.06
    POSITIVE LOGITS
     الأربع
    0.08
     حال
    0.07
    OUT
    0.07
     buurt
    0.07
    更换
    0.07
    =\""
    0.07
     Books
    0.07
    的不同
    0.07
    Field
    0.07
    捆
    0.07
    Act Density 0.003%

    No Known Activations