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

    Neuronpedia

    INDEX
    Explanations

    immigration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pilgr
    -0.06
    观看
    -0.06
     Depart
    -0.06
     crew
    -0.06
    耳
    -0.06
    _reason
    -0.06
     Minh
    -0.06
    果
    -0.06
     Huffington
    -0.06
     Zhang
    -0.06
    POSITIVE LOGITS
    航空
    0.07
    ()-
    0.07
    اس
    0.06
     О
    0.06
     notwithstanding
    0.06
     shortages
    0.06
    ┴
    0.06
    __(*
    0.06
    िनक
    0.06
     because
    0.06
    Act Density 0.039%

    No Known Activations