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

    Neuronpedia

    INDEX
    Explanations

    code constructs and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ühlen
    0.41
    蛲
    0.39
     أوروب
    0.38
    人と
    0.37
    落ち着
    0.36
     выйти
    0.36
    圍
    0.35
     للنساء
    0.35
     नींद
    0.35
     Lembrando
    0.35
    POSITIVE LOGITS
    ↵
    0.57
     的
    0.43
    "
    0.43
     শীর্ষক
    0.42
     ，
    0.41
    これは
    0.39
     -->
    0.38
     translates
    0.38
     translate
    0.37
    os
    0.37
    Act Density 0.249%

    No Known Activations