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

    Neuronpedia

    INDEX
    Explanations

    tax credits and deductions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ל
    2.23
    o
    2.02
    ت
    2.02
    يًا
    1.94
    ள்ளது
    1.86
    t
    1.86
    ن
    1.84
    s
    1.84
    ح
    1.79
    ంలో
    1.76
    POSITIVE LOGITS
    ер
    1.62
    𝙈
    1.45
    ্যাড
    1.44
    ১৮
    1.40
    ###########
    1.37
    𝙊
    1.37
     क
    1.35
    ができ
    1.34
    ้
    1.33
    ︎
    1.32
    Act Density 0.007%

    No Known Activations