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

    Neuronpedia

    INDEX
    Explanations

    biggest, largest, suitable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ،
    0.76
    ၊
    0.64
    But
    0.64
     però
    0.61
    :
    0.61
     แต่
    0.60
    回忆
    0.59
    }$,
    0.58
     فقط
    0.57
    ARE
    0.57
    POSITIVE LOGITS
    ？）
    0.62
     RAS
    0.57
    ത്തിലുള്ള
    0.56
     candlestick
    0.54
     chiral
    0.52
     તેમના
    0.52
     त्यांची
    0.52
     fluorine
    0.52
     Pepsi
    0.51
     camshaft
    0.51
    Act Density 0.990%

    No Known Activations