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

    Neuronpedia

    INDEX
    Explanations

    numbers and counting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     таких
    0.57
    这类
    0.56
     Такие
    0.52
     такими
    0.52
     dessas
    0.51
     takich
    0.51
    そういう
    0.50
    those
    0.48
     those
    0.47
     সেসব
    0.46
    POSITIVE LOGITS
     three
    0.61
     drei
    0.58
     two
    0.54
     five
    0.54
    三个
    0.53
    三個
    0.53
     following
    0.51
     four
    0.51
     six
    0.51
    ollowing
    0.51
    Act Density 0.002%

    No Known Activations