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

    Neuronpedia

    INDEX
    Explanations

    FROM

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    jwt
    -0.07
    我的
    -0.07
    chandle
    -0.06
     thereof
    -0.06
    gif
    -0.06
    ($.
    -0.06
    ику
    -0.06
     Jas
    -0.06
    buie
    -0.06
    izabeth
    -0.06
    POSITIVE LOGITS
    olie
    0.07
    atural
    0.07
     민
    0.06
    -graph
    0.06
     Fantasy
    0.06
     Fur
    0.06
    -private
    0.06
    ammer
    0.06
     や
    0.06
     vk
    0.06
    Act Density 0.001%

    No Known Activations