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
     reb
    -0.06
    اتف
    -0.06
     Canal
    -0.06
     seh
    -0.06
     lawyer
    -0.06
    .da
    -0.06
     weir
    -0.06
     wan
    -0.06
     very
    -0.06
     Лу
    -0.06
    POSITIVE LOGITS
     sóng
    0.08
    against
    0.07
     downturn
    0.06
    .Once
    0.06
     ****************
    0.06
    ButtonClick
    0.06
     بسبب
    0.06
    voie
    0.06
    vang
    0.06
    قلال
    0.06
    Act Density 0.008%

    No Known Activations