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

    Neuronpedia

    INDEX
    Explanations

    want to find

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Carnival
    0.43
     включая
    0.42
    》（
    0.41
    的网络
    0.39
     বেশিরভাগ
    0.39
    驱
    0.39
     Dolls
    0.39
     большин
    0.38
     większość
    0.38
    আপনার
    0.38
    POSITIVE LOGITS
    找出
    0.65
     determinar
    0.63
     determine
    0.63
     evaluar
    0.59
     найти
    0.55
     capire
    0.50
     how
    0.49
     devise
    0.49
     encontrar
    0.49
     apakah
    0.49
    Act Density 0.148%

    No Known Activations