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

    Neuronpedia

    INDEX
    Explanations

    naming

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ل
    0.95
    人员
    0.87
     incipient
    0.82
     antico
    0.80
     Ancient
    0.80
    锻炼
    0.79
    为空
    0.78
    usive
    0.77
    要注意
    0.76
     reciproc
    0.75
    POSITIVE LOGITS
    vy
    0.86
     glance
    0.86
    bitcoin
    0.85
     metų
    0.82
    ഷ
    0.80
    ية
    0.80
    жды
    0.80
    🏻
    0.79
    ger
    0.79
    𝘁
    0.78
    Act Density 0.278%

    No Known Activations