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

    Neuronpedia

    INDEX
    Explanations

    another positive resource or option

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ।
    0.77
    。
    0.76
    ות
    0.74
     plasmids
    0.69
     napkins
    0.66
     invertebrates
    0.61
    рс
    0.60
    ,’”
    0.59
     solitons
    0.59
    :\
    0.59
    POSITIVE LOGITS
     περίπτωση
    0.60
    n
    0.59
    기
    0.57
    場合
    0.55
    ración
    0.54
     Kirchen
    0.54
    set
    0.54
     ጊዜ
    0.53
    درسة
    0.53
    féle
    0.53
    Act Density 0.029%

    No Known Activations