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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     состав
    -0.08
    १�
    -0.07
    (Convert
    -0.07
     invit
    -0.06
     bonds
    -0.06
     Weinstein
    -0.06
     Eag
    -0.06
    /products
    -0.06
    iras
    -0.06
    CW
    -0.06
    POSITIVE LOGITS
    =\"";↵
    0.07
     longtime
    0.06
     факти
    0.06
    _theme
    0.06
    'value
    0.06
    -S
    0.06
    ['__
    0.06
    �示
    0.06
    _methods
    0.06
    ’dan
    0.06
    Act Density 0.001%

    No Known Activations