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

    Neuronpedia

    INDEX
    Explanations

    Emp

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	unit
    -0.07
     （
    -0.07
     produtos
    -0.06
     mutations
    -0.06
     ned
    -0.06
    観
    -0.06
     proteins
    -0.06
    иты
    -0.06
    _form
    -0.06
     cur
    -0.06
    POSITIVE LOGITS
     Venezuelan
    0.07
     populous
    0.06
     wenig
    0.06
     جنوب
    0.06
    hipster
    0.06
     μά
    0.06
     چنین
    0.06
     TWO
    0.06
    基于
    0.06
     Hollande
    0.06
    Act Density 0.249%

    No Known Activations