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

    Neuronpedia

    INDEX
    Explanations

    code release

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     contribu
    0.44
     download
    0.43
     thank
    0.43
    subscription
    0.42
    бай
    0.42
     fread
    0.42
     subscription
    0.41
     kg
    0.41
    kg
    0.40
     contributor
    0.40
    POSITIVE LOGITS
    匿名
    0.43
    xxxxxxxx
    0.42
    CodeDict
    0.39
    atoria
    0.39
     queremos
    0.39
    aremos
    0.39
     चाहती
    0.39
    为了
    0.39
    已
    0.39
    是否存在
    0.38
    Act Density 0.008%

    No Known Activations