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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    秆
    -0.07
    ////////////////////////////////////////////////////////////////////////////////////////////////
    -0.07
     getClient
    -0.07
     książki
    -0.07
    륜
    -0.07
    _sizes
    -0.07
    ar
    -0.07
     mixer
    -0.07
    ▻
    -0.07
    _usb
    -0.06
    POSITIVE LOGITS
    ꧊
    0.07
     פו
    0.06
    平行
    0.06
    го
    0.06
     Fundamental
    0.06
    Selectors
    0.06
     Regulation
    0.06
     fri
    0.06
    fortunately
    0.06
    companies
    0.06
    Act Density 0.019%

    No Known Activations