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

    Neuronpedia

    INDEX
    Explanations

    long term benefits and plans

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ار
    1.63
    ول
    1.55
     macam
    1.55
    Sumber
    1.54
    Бе
    1.46
    ال
    1.45
     السكان
    1.45
    زمین
    1.43
     croissant
    1.43
    ្នុង
    1.42
    POSITIVE LOGITS
    ל
    1.55
     awhile
    1.51
    ل
    1.38
    cale
    1.34
    ліся
    1.30
     duração
    1.30
    ق
    1.30
    ђ
    1.30
    ник
    1.28
    szer
    1.28
    Act Density 0.105%

    No Known Activations