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

    Neuronpedia

    INDEX
    Explanations

    chip

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    计算
    -0.07
    Seeing
    -0.07
    _ACCESS
    -0.06
    ну
    -0.06
     Norte
    -0.06
    不足
    -0.06
    แท
    -0.06
     المح
    -0.06
    -conf
    -0.06
    Ngày
    -0.06
    POSITIVE LOGITS
    (startTime
    0.07
    .Retrofit
    0.06
     sensational
    0.06
    Enumeration
    0.06
    locator
    0.06
    atural
    0.06
    (rot
    0.06
    ?");↵
    0.06
     nj
    0.06
    desk
    0.06
    Act Density 0.014%

    No Known Activations