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

    Neuronpedia

    INDEX
    Explanations

    paper

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (redis
    -0.07
    程序
    -0.06
    _Store
    -0.06
    wi
    -0.06
     cherish
    -0.06
    +]
    -0.06
     Nursery
    -0.06
    /^
    -0.06
     Want
    -0.06
     collegiate
    -0.06
    POSITIVE LOGITS
     ElementType
    0.08
    .UserService
    0.07
    strconv
    0.07
     aftermarket
    0.07
     explained
    0.07
     kiểu
    0.07
    的方法
    0.07
    Parts
    0.07
    年后
    0.07
    变异
    0.07
    Act Density 0.018%

    No Known Activations