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

    Neuronpedia

    INDEX
    Explanations

    informal greetings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    であれば
    0.75
     ماذا
    0.75
     спектак
    0.69
    ⑰
    0.68
    しているので
    0.65
    代替
    0.64
     Nz
    0.64
     كند
    0.64
     equivalent
    0.62
    <unused346>
    0.62
    POSITIVE LOGITS
     ya
    2.01
     outta
    1.95
     yer
    1.81
     gonna
    1.79
     goin
    1.71
     yah
    1.59
     wanna
    1.58
     gotta
    1.56
     lotta
    1.53
     Gonna
    1.50
    Act Density 0.576%

    No Known Activations