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

    Neuronpedia

    INDEX
    Explanations

    ="

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    面积
    -0.07
     agree
    -0.07
    alking
    -0.07
     homes
    -0.07
     rot
    -0.07
     halten
    -0.07
     clustering
    -0.07
     aluminum
    -0.07
    -align
    -0.07
     homepage
    -0.07
    POSITIVE LOGITS
    وذ
    0.07
    פוליט
    0.07
    嘬
    0.07
    再度
    0.07
    \Resource
    0.07
     Episodes
    0.07
    /linux
    0.07
    מתח
    0.06
    튕
    0.06
    榑
    0.06
    Act Density 0.111%

    No Known Activations