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

    Neuronpedia

    INDEX
    Explanations

    It is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    apparition
    0.45
    偶然
    0.43
    蘖
    0.43
     apari
    0.42
    osexuality
    0.41
     считать
    0.41
     робити
    0.41
    ravariant
    0.41
    GUNDABAD
    0.40
    飲む
    0.40
    POSITIVE LOGITS
     is
    0.56
     represents
    0.48
     supplement
    0.48
     takes
    0.46
     utilizes
    0.46
     Is
    0.45
     utilises
    0.44
     can
    0.43
     remains
    0.43
     Sal
    0.42
    Act Density 0.001%

    No Known Activations