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

    Neuronpedia

    INDEX
    Explanations

    library

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =val
    -0.07
    ßerdem
    -0.07
    操作系统
    -0.06
    　
    -0.06
    (_
    -0.06
     Dominic
    -0.06
    信箱
    -0.06
    pecia
    -0.06
    pitch
    -0.06
     gpio
    -0.06
    POSITIVE LOGITS
     WOW
    0.07
     biologist
    0.07
    集合
    0.07
    ㋑
    0.06
    ===========
    0.06
    嵲
    0.06
    냘
    0.06
     PUT
    0.06
     raining
    0.06
    吆
    0.06
    Act Density 0.009%

    No Known Activations