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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    isActive
    -0.07
    千伏
    -0.07
    릳
    -0.07
    ING
    -0.07
    ogra
    -0.06
    景德
    -0.06
    ऊ
    -0.06
     magnet
    -0.06
     ổn
    -0.06
     Malone
    -0.06
    POSITIVE LOGITS
     должны
    0.07
    憔
    0.06
     fille
    0.06
     позволит
    0.06
     تقوم
    0.06
     proyectos
    0.06
     우리
    0.06
    的新
    0.06
    CAL
    0.06
    recipes
    0.06
    Act Density 0.002%

    No Known Activations