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

    Neuronpedia

    INDEX
    Explanations

    Doubles/multiple versions of people

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     compr
    -0.07
     apologize
    -0.07
     apologise
    -0.06
    _quit
    -0.06
    (NAME
    -0.06
     governor
    -0.06
     Instead
    -0.06
    imos
    -0.06
    -states
    -0.06
    (comment
    -0.06
    POSITIVE LOGITS
     जब
    0.07
     illusions
    0.07
     Higher
    0.07
    */),
    0.07
    (pc
    0.07
    >';
↵
    0.06
     ArgumentNullException
    0.06
    [_
    0.06
     생산
    0.06
    ous
    0.06
    Act Density 0.013%

    No Known Activations