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

    Neuronpedia

    INDEX
    Explanations

    Income tax and limits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ിയുടെ
    1.14
    म
    1.10
    し
    1.10
    اج
    1.09
    மாக
    1.03
    り
    1.02
    مة
    0.99
    وم
    0.95
    الم
    0.94
    يا
    0.93
    POSITIVE LOGITS
     Income
    1.33
    "
    1.28
     income
    1.27
    a
    1.20
    th
    1.16
    2
    1.13
    Income
    1.08
     earners
    1.08
    e
    1.07
    ert
    1.06
    Act Density 0.011%

    No Known Activations