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

    Neuronpedia

    INDEX
    Explanations

    Non-English text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rootNode
    -0.09
    最受欢迎
    -0.07
    เอง
    -0.07
    ytt
    -0.07
    佺
    -0.07
    ","#
    -0.07
    Best
    -0.07
    عداد
    -0.07
    榉
    -0.07
    欣
    -0.06
    POSITIVE LOGITS
    ры
    0.08
    遗留
    0.07
    𒋗
    0.07
     годы
    0.07
    cha
    0.07
     letz
    0.07
     dalla
    0.07
     docs
    0.06
     duplex
    0.06
    執
    0.06
    Act Density 0.011%

    No Known Activations