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

    Neuronpedia

    INDEX
    Explanations

    deep learning, neural networks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    午
    -0.09
     analizar
    -0.08
    ighteous
    -0.07
     이상
    -0.07
     Lesser
    -0.07
     trays
    -0.07
    roma
    -0.07
     Employees
    -0.07
     broth
    -0.07
     Intent
    -0.07
    POSITIVE LOGITS
     leistungs
    0.11
     exploiting
    0.10
     breakthroughs
    0.10
    近年来
    0.09
    旗舰
    0.09
     performant
    0.09
     exploit
    0.09
     breakthrough
    0.09
     powerful
    0.08
    突破
    0.08
    Act Density 0.010%

    No Known Activations