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

    Neuronpedia

    INDEX
    Explanations

    Political plans and policies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Trap
    -0.07
    	status
    -0.07
    _service
    -0.07
     trap
    -0.06
    Dependencies
    -0.06
    рун
    -0.06
     patriarch
    -0.06
    itions
    -0.06
    стру
    -0.06
    елей
    -0.06
    POSITIVE LOGITS
    Cannot
    0.08
     �
    0.07
     JFK
    0.06
     Slav
    0.06
    iid
    0.06
     неприят
    0.06
     ORD
    0.06
    。↵↵↵↵↵↵
    0.06
     Latest
    0.06
    IMPORTANT
    0.06
    Act Density 0.034%

    No Known Activations