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

    Neuronpedia

    INDEX
    Explanations

    tokenization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    षक
    0.42
    Lovely
    0.38
    RELATIVE
    0.37
    ่าน
    0.36
    身上的
    0.36
    પાસ
    0.36
     લખ
    0.36
    기고
    0.36
    ohy
    0.35
     ठाकरे
    0.35
    POSITIVE LOGITS
     Zoo
    0.40
     Builder
    0.39
    溂
    0.39
     comments
    0.38
     Fast
    0.38
     Bakker
    0.38
    ős
    0.38
    タイプ
    0.37
     Comments
    0.37
    ősz
    0.37
    Act Density 0.000%

    No Known Activations