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

    Neuronpedia

    INDEX
    Explanations

    prime numbers and their properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    主要
    0.51
    大
    0.45
    球
    0.43
    就
    0.42
    主
    0.42
    ，
    0.42
    屋
    0.42
    No
    0.41
    通
    0.41
    PhCH
    0.41
    POSITIVE LOGITS
    rawberry
    0.53
     satisf
    0.49
     médioc
    0.49
    ())+
    0.48
     whack
    0.47
     shameless
    0.47
     États
    0.47
     diversité
    0.47
    🕗
    0.46
     spreads
    0.46
    Act Density 0.006%

    No Known Activations