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

    Neuronpedia

    INDEX
    Explanations

    government ministries/ministers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     comunic
    -0.07
    -pe
    -0.06
     typical
    -0.06
     Magnum
    -0.06
     افراد
    -0.06
    (report
    -0.06
     AM
    -0.06
    IGO
    -0.06
    	write
    -0.06
    Letter
    -0.06
    POSITIVE LOGITS
    设计器
    0.06
    ,:),
    0.06
     �
    0.06
    CLAIM
    0.06
     itemBuilder
    0.06
    .hardware
    0.06
     <%=
    0.06
    rodu
    0.06
     mHandler
    0.06
     conglomer
    0.06
    Act Density 0.077%

    No Known Activations