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

    Neuronpedia

    INDEX
    Explanations

    processes/sequences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     upright
    -0.07
    .filename
    -0.07
     Disclaimer
    -0.06
     neutrality
    -0.06
     тут
    -0.06
    Among
    -0.06
     einer
    -0.06
     alb
    -0.06
    Hello
    -0.06
     Damon
    -0.06
    POSITIVE LOGITS
    .'
    0.07
     CRA
    0.07
     exploited
    0.07
    ['<{
    0.06
    	Resource
    0.06
     SSC
    0.06
     PUS
    0.06
    obec
    0.06
    ."),↵
    0.06
    idade
    0.06
    Act Density 0.019%

    No Known Activations