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

    Neuronpedia

    INDEX
    Explanations

    text analysis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    的竞争
    -0.08
    ansson
    -0.07
     stature
    -0.07
    牖
    -0.06
     furnished
    -0.06
     tú
    -0.06
     intric
    -0.06
    🏴
    -0.06
    羁
    -0.06
    立法
    -0.06
    POSITIVE LOGITS
     Andres
    0.07
    (binding
    0.07
    ql
    0.07
    כונים
    0.07
     Moderate
    0.06
     underside
    0.06
    экон
    0.06
    鲾
    0.06
     healthy
    0.06
    (cl
    0.06
    Act Density 0.016%

    No Known Activations