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

    Neuronpedia

    INDEX
    Explanations

    professional closings and well wishes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     aforementioned
    0.44
    つまり
    0.44
     কারণে
    0.43
     subconsciously
    0.43
     certes
    0.43
    sometimes
    0.41
     (!)
    0.41
    =
    0.41
     admittedly
    0.40
     있고요
    0.40
    POSITIVE LOGITS
    ！
    0.55
    !</
    0.53
    !`
    0.53
     🎉
    0.53
    !",
    0.50
    !
    0.50
    !")
    0.49
     Regards
    0.48
    ﹗
    0.48
    !';
    0.48
    Act Density 0.004%

    No Known Activations