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

    Neuronpedia

    INDEX
    Explanations

    tax planning strategies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ש
    1.42
    ний
    1.37
     وبين
    1.30
     HOA
    1.25
     dotycz
    1.24
     gange
    1.24
     Đặc
    1.17
    nasium
    1.16
    ти
    1.16
    ഴ
    1.16
    POSITIVE LOGITS
    IM
    1.68
    ع
    1.61
    ين
    1.46
    。,
    1.39
     وعند
    1.36
    。
    1.36
    ),
    1.34
    ।
    1.34
    un
    1.34
    élim
    1.34
    Act Density 0.002%

    No Known Activations