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

    Neuronpedia

    INDEX
    Explanations

    Qt views and images

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     UILabel
    0.43
    ("/",
    0.39
    霢
    0.39
     reviewer
    0.39
    のアレンジ
    0.39
     리뷰
    0.38
    ധാന
    0.38
     reff
    0.38
    ड़िया
    0.37
     enriching
    0.37
    POSITIVE LOGITS
    kos
    0.43
    eled
    0.43
    stern
    0.39
    mor
    0.39
    î
    0.38
    Î
    0.38
    Ex
    0.37
    bt
    0.37
     кос
    0.36
    yar
    0.36
    Act Density 0.000%

    No Known Activations