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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    7
    -0.07
     furnished
    -0.07
     ashes
    -0.07
     respect
    -0.07
    _TH
    -0.06
    ith
    -0.06
    4
    -0.06
     Mary
    -0.06
     Hannah
    -0.06
    uty
    -0.06
    POSITIVE LOGITS
    248
    0.08
    568
    0.08
    0.08
    268
    0.08
    เอง
    0.08
     Jones
    0.07
    (for
    0.07
    ��
    0.07
    鐘
    0.07
    768
    0.07
    Act Density 0.067%

    No Known Activations