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

    Neuronpedia

    INDEX
    Explanations

    beyond just

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ويل
    0.47
     delimiters
    0.44
    ائ
    0.44
    лиз
    0.43
    婁
    0.43
    عة
    0.43
    وعة
    0.41
     হিসাব
    0.41
    ولات
    0.40
    痤
    0.40
    POSITIVE LOGITS
     Angus
    0.42
     Musica
    0.40
     Chan
    0.40
    gift
    0.39
     Sr
    0.38
     magnific
    0.38
     certainly
    0.38
    singer
    0.38
     Picture
    0.38
    ="";
    0.38
    Act Density 0.001%

    No Known Activations