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

    Neuronpedia

    INDEX
    Explanations

    be

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     eslint
    -0.07
    .ef
    -0.07
     mówi
    -0.07
     ef
    -0.07
     astronomers
    -0.07
     ночь
    -0.06
    ////////////////////////////////////////////////////////////////////////
    -0.06
     гос
    -0.06
     metropolitan
    -0.06
     решил
    -0.06
    POSITIVE LOGITS
    ҧ
    0.08
    热潮
    0.08
    cart
    0.07
     Хотя
    0.07
    WA
    0.07
    dam
    0.07
     singers
    0.07
     Song
    0.07
    也
    0.07
    ("&
    0.06
    Act Density 0.001%

    No Known Activations