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

    Neuronpedia

    INDEX
    Explanations

    parentheses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .GetMapping
    -0.07
    활동
    -0.07
    净值
    -0.07
    쎗
    -0.07
     Education
    -0.07
     Vie
    -0.06
    になっている
    -0.06
    穰
    -0.06
     Tor
    -0.06
    ensity
    -0.06
    POSITIVE LOGITS
    правля
    0.07
     deals
    0.07
    drawer
    0.07
    ipher
    0.07
    _lowercase
    0.07
     shuts
    0.07
    промышлен
    0.07
    userRepository
    0.07
    beam
    0.07
    公开发
    0.07
    Act Density 0.013%

    No Known Activations