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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    回去
    -0.07
     vy
    -0.07
     fun
    -0.07
    合伙
    -0.07
    鼓励
    -0.07
    elope
    -0.06
     viewPager
    -0.06
    刚
    -0.06
     initView
    -0.06
    发育
    -0.06
    POSITIVE LOGITS
     buds
    0.07
     alumnos
    0.07
    ものは
    0.07
    <title
    0.07
     fires
    0.07
    ubits
    0.07
    rates
    0.07
    刊物
    0.07
    .amazon
    0.07
    ней
    0.07
    Act Density 0.008%

    No Known Activations