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

    Neuronpedia

    INDEX
    Explanations

    money growth and value

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ben
    0.42
     هستیم
    0.40
     ಸಲ
    0.39
     Ease
    0.38
    ర్కొ
    0.37
     Ile
    0.37
    >∕</
    0.37
    是什么
    0.37
     Mor
    0.37
    anness
    0.37
    POSITIVE LOGITS
     раст
    0.58
     deposit
    0.56
     snowball
    0.56
     grows
    0.54
     deposited
    0.54
     crece
    0.53
    deposit
    0.50
     sum
    0.50
     büy
    0.48
     сумма
    0.48
    Act Density 0.002%

    No Known Activations