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

    Neuronpedia

    INDEX
    Explanations

    photo upload

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     besonderen
    0.45
     vissa
    0.45
     certains
    0.43
     tertentu
    0.42
     alguns
    0.42
     некоторые
    0.42
     некоторых
    0.42
     bepaalde
    0.41
     niektórych
    0.41
    的一些
    0.40
    POSITIVE LOGITS
     جميع
    0.39
    🥇
    0.37
     aka
    0.36
     the
    0.35
    🚀
    0.35
     completely
    0.35
     either
    0.34
     completo
    0.34
    🏆
    0.34
     ✅
    0.33
    Act Density 0.624%

    No Known Activations