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

    Neuronpedia

    INDEX
    Explanations

    theatrical releases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     управля
    -0.09
    /control
    -0.07
    -0.07
    IO
    -0.07
     বিষয়ে
    -0.07
    quart
    -0.07
    闲
    -0.07
     Incorpor
    -0.07
     Sofa
    -0.07
     incorporating
    -0.07
    POSITIVE LOGITS
     worldwide
    0.10
     Worldwide
    0.09
     brasileiras
    0.09
    êmica
    0.09
     acclaim
    0.08
     enlisted
    0.08
     çı
    0.08
     Strait
    0.08
     tutti
    0.08
    模式
    0.08
    Act Density 0.008%
    No Known Activations