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

    Neuronpedia

    INDEX
    Explanations

    juegos de cartas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Atual
    0.54
    izquierda
    0.51
    Ли
    0.51
    uerpo
    0.48
    TxtArea
    0.47
    Esp
    0.47
    getNome
    0.47
    Cau
    0.47
    Inicio
    0.46
    occasione
    0.46
    POSITIVE LOGITS
     si
    0.80
     la
    0.62
     Si
    0.58
     se
    0.58
     existe
    0.52
     exists
    0.52
     일반적으로
    0.52
     exist
    0.50
     là
    0.49
    一般来说
    0.48
    Act Density 0.281%

    No Known Activations