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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -series
    -0.07
    _usb
    -0.07
    -two
    -0.07
    :model
    -0.07
     FT
    -0.07
    _out
    -0.07
     evenings
    -0.07
     平
    -0.06
    _Out
    -0.06
     Lok
    -0.06
    POSITIVE LOGITS
    sınız
    0.06
    _BORDER
    0.06
     전국
    0.06
     اینتر
    0.06
     탐
    0.06
    евид
    0.06
    glich
    0.06
    信息
    0.06
    ipop
    0.06
    <src
    0.06
    Act Density 0.027%

    No Known Activations