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

    Neuronpedia

    INDEX
    Explanations

    named entities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _arg
    -0.06
    Dal
    -0.06
     lock
    -0.06
     terminated
    -0.06
    殺
    -0.06
    	req
    -0.06
     dog
    -0.06
    .dp
    -0.06
     Tutorial
    -0.06
     gamer
    -0.06
    POSITIVE LOGITS
    (PARAM
    0.07
     같이
    0.07
    xious
    0.06
          ↵      ↵
    0.06
    percentage
    0.06
    _unicode
    0.06
     \↵↵
    0.06
                   ↵
    0.06
     upstairs
    0.06
    ystore
    0.06
    Act Density 0.103%

    No Known Activations