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

    Neuronpedia

    INDEX
    Explanations

    cause and effect

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    这一点
    0.58
    这点
    0.54
     важных
    0.51
     wichtig
    0.50
     thats
    0.50
     importantly
    0.49
     중요
    0.49
     중요한
    0.47
    是一個
    0.46
     కూడా
    0.46
    POSITIVE LOGITS
     ஏனெனில்
    0.52
    因为它
    0.52
    Basically
    0.51
     কেননা
    0.50
    不仅
    0.50
     fordi
    0.50
     زیرا
    0.49
     Bởi
    0.48
     it
    0.48
    because
    0.48
    Act Density 0.004%

    No Known Activations