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

    Neuronpedia

    INDEX
    Explanations

    Code and foreign languages

    np_max-act-logits · gemini-2.0-flashTriggered by @bettyfeng2003
    New Auto-Interp
    Negative Logits
    (zone
    -0.07
    严厉打击
    -0.07
    梃
    -0.07
    	query
    -0.06
    rise
    -0.06
    讨厌
    -0.06
    ETweet
    -0.06
     ADA
    -0.06
     Inquiry
    -0.06
    **↵
    -0.06
    POSITIVE LOGITS
     والس
    0.07
    insk
    0.07
    ホ
    0.07
     mamm
    0.07
    最难
    0.07
    UGC
    0.07
    _EVENTS
    0.07
    جال
    0.07
    ܦ
    0.07
    電話及
    0.06
    Act Density 0.237%

    No Known Activations