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

    Neuronpedia

    INDEX
    Explanations

    names followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    दर्शिता
    0.34
    ্ণ
    0.33
     품질
    0.32
     Ayrshire
    0.32
     micrograms
    0.32
     -->'
    0.31
    云南
    0.31
    可能です
    0.31
    性和
    0.31
     intrav
    0.31
    POSITIVE LOGITS
    ،
    0.49
     ơi
    0.49
     please
    0.49
     hãy
    0.43
    ，
    0.43
     querida
    0.41
     спасибо
    0.41
    你好
    0.39
    ၊
    0.39
    请
    0.39
    Act Density 0.042%

    No Known Activations