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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     الى
    -0.08
    词
    -0.06
     coveted
    -0.06
     Тут
    -0.06
     disdain
    -0.06
    어가
    -0.06
     shaders
    -0.06
    .solution
    -0.06
     outings
    -0.06
     tamil
    -0.06
    POSITIVE LOGITS
    ?>↵
    0.06
    PushMatrix
    0.06
    形式
    0.06
     nắng
    0.06
     fell
    0.06
     sadd
    0.06
     eğ
    0.06
     단
    0.06
     Mrs
    0.06
     glazed
    0.06
    Act Density 0.048%

    No Known Activations