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

    Neuronpedia

    INDEX
    Explanations

    dear [name/team] or programming terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ind
    0.45
    wesen
    0.42
    ̌
    0.40
    im
    0.39
    imiz
    0.39
    aven
    0.38
     attending
    0.38
    στη
    0.38
    alone
    0.38
    anjian
    0.38
    POSITIVE LOGITS
    网友
    0.68
     pandas
    0.61
    網友
    0.59
     уважаемые
    0.58
     guys
    0.57
     classmates
    0.55
     folks
    0.52
     форум
    0.52
    小伙伴
    0.52
     asyncio
    0.51
    Act Density 0.000%

    No Known Activations