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

    Neuronpedia

    INDEX
    Explanations

    Chinese conjunctions and prepositions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    骂
    0.50
     není
    0.49
     然后
    0.48
     ordinairement
    0.47
     转
    0.47
    胫
    0.47
     рези
    0.47
     машиналарын
    0.47
     эмне
    0.47
     машиналары
    0.47
    POSITIVE LOGITS
    一方面
    0.56
     dazzling
    0.49
    Y
    0.44
    据悉
    0.43
     Chinese
    0.42
     longing
    0.42
     netizens
    0.42
     renowned
    0.41
     WeChat
    0.40
    venue
    0.40
    Act Density 0.007%

    No Known Activations