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

    Neuronpedia

    INDEX
    Explanations

    asking questions to find common interests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     patriarchal
    0.59
     curvil
    0.49
     intravascular
    0.49
     metaphorical
    0.48
     extractive
    0.47
    赋值
    0.47
     simplification
    0.47
     transformative
    0.46
     causative
    0.46
     ಅಂಶ
    0.46
    POSITIVE LOGITS
     meetup
    0.69
     guys
    0.62
     weekend
    0.59
     Join
    0.58
     Guys
    0.57
     saturday
    0.56
     Meet
    0.55
     newbie
    0.54
     congrats
    0.54
     joins
    0.54
    Act Density 0.023%

    No Known Activations