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

    Neuronpedia

    INDEX
    Explanations

    socioeconomic status

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    辟
    -0.08
     вз
    -0.07
    登场
    -0.07
    Registered
    -0.07
     embrace
    -0.06
     представ
    -0.06
    رأس
    -0.06
     pant
    -0.06
    ��
    -0.06
     visibility
    -0.06
    POSITIVE LOGITS
    全市
    0.08
     propagated
    0.07
    同じ
    0.07
    実際に
    0.07
    슌
    0.06
    ynchron
    0.06
    (Return
    0.06
     Monica
    0.06
    🚨
    0.06
    ')."
    0.06
    Act Density 0.018%

    No Known Activations