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

    Neuronpedia

    INDEX
    Explanations

    introductions to explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    သော
    0.59
     ofthe
    0.56
    новая
    0.54
    Fundamentals
    0.54
    Aux
    0.54
    Predicted
    0.51
    ของ
    0.51
    hepatic
    0.49
    legends
    0.49
     Aux
    0.49
    POSITIVE LOGITS
     here
    0.94
     aqui
    0.73
    :
    0.70
     aquí
    0.70
     aici
    0.67
     εδώ
    0.66
     тут
    0.61
     acá
    0.60
     tutaj
    0.59
    ここは
    0.58
    Act Density 1.011%

    No Known Activations