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

    Neuronpedia

    INDEX
    Explanations

    WeChat mini-programs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Mort
    0.47
     plenum
    0.47
     Iraqi
    0.43
     عراق
    0.42
    矯
    0.41
    Fear
    0.41
    獸
    0.40
    Kö
    0.40
    Think
    0.39
    Brook
    0.39
    POSITIVE LOGITS
     WeChat
    0.70
    小程序
    0.68
    wx
    0.68
    微信
    0.67
     wx
    0.57
     Tencent
    0.55
     WhatsApp
    0.54
     Shopify
    0.50
     Tenerife
    0.48
    StorageSync
    0.47
    Act Density 0.002%

    No Known Activations