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

    Neuronpedia

    INDEX
    Explanations

    TV show descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    isty
    -0.06
     sociale
    -0.06
    환경
    -0.06
     nghiệ
    -0.06
    _NODES
    -0.06
     Citizen
    -0.06
     выполн
    -0.06
     Estate
    -0.06
     ceramic
    -0.06
     gå
    -0.06
    POSITIVE LOGITS
     Couldn
    0.07
    Interested
    0.07
    }")↵↵
    0.07
     mix
    0.07
     Donald
    0.06
    monton
    0.06
     desirable
    0.06
    )),↵
    0.06
    <Select
    0.06
     ]);↵
    0.06
    Act Density 0.032%

    No Known Activations