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

    Neuronpedia

    INDEX
    Explanations

    questioning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Thats
    0.49
    那你
    0.49
     ولكن
    0.48
     ถ้า
    0.48
     lekin
    0.48
     Nhưng
    0.48
     então
    0.47
     그러면은
    0.47
    Thats
    0.47
     entonces
    0.47
    POSITIVE LOGITS
    自带
    0.43
    需求
    0.42
     ওরফে
    0.41
    类似于
    0.41
     gossip
    0.39
     Metadata
    0.39
     zejména
    0.39
    অর্থাৎ
    0.39
    韻
    0.38
    MILLISE
    0.38
    Act Density 0.071%

    No Known Activations