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

    Neuronpedia

    INDEX
    Explanations

    multilingual sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    。
    0.30
    கிறது
    0.24
     ఉంటుంది
    0.24
    します
    0.23
    ります
    0.23
    ครับ
    0.23
    。\
    0.23
    ค่ะ
    0.22
     있다
    0.22
     있습니다
    0.22
    POSITIVE LOGITS
     ਨੂੰ
    0.29
    റിന്റെ
    0.27
     more
    0.26
     యొక్క
    0.25
    માં
    0.25
     को
    0.25
    નો
    0.24
    의
    0.24
    를
    0.23
    ના
    0.23
    Act Density 0.016%

    No Known Activations