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

    Neuronpedia

    INDEX
    Explanations

    Error Handling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    enter
    1.13
    od
    1.08
    istika
    1.05
     entend
    1.02
    ez
    1.01
    electron
    1.00
    chloride
    1.00
    이고
    1.00
    이면
    0.98
     autant
    0.98
    POSITIVE LOGITS
     الخاصة
    1.11
    ט
    1.09
    ны
    1.08
    い
    1.08
     Боль
    1.03
    י
    1.02
    ত
    1.00
    เป็น
    0.97
     Cardinals
    0.97
    น
    0.96
    Act Density 0.020%

    No Known Activations