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

    Neuronpedia

    INDEX
    Explanations

    terms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Host
    -0.08
    пол
    -0.07
    ----↵↵
    -0.07
    sc
    -0.07
     navigating
    -0.07
     분
    -0.07
     length
    -0.06
    _As
    -0.06
    	test
    -0.06
    _RG
    -0.06
    POSITIVE LOGITS
     הל
    0.08
    ophobia
    0.08
     Eighth
    0.07
    ителей
    0.07
    refixer
    0.07
    九十
    0.06
     Macy
    0.06
    הוצאה
    0.06
     الذى
    0.06
     Phạm
    0.06
    Act Density 0.001%

    No Known Activations