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

    Neuronpedia

    INDEX
    Explanations

    limits and boundaries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Me
    -0.07
     مع
    -0.06
     проект
    -0.06
     Oper
    -0.06
    .svg
    -0.06
    閉
    -0.06
    show
    -0.06
    ERN
    -0.06
    显
    -0.06
    ��
    -0.06
    POSITIVE LOGITS
     هناك
    0.07
     Relations
    0.07
     kvinnor
    0.06
    /question
    0.06
     relations
    0.06
    -law
    0.06
     vol
    0.06
     Kathy
    0.06
    	th
    0.06
     omez
    0.06
    Act Density 0.178%

    No Known Activations