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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ){
↵
↵
    -0.07
     calendars
    -0.06
    지가
    -0.06
     خواهند
    -0.06
     malware
    -0.06
    David
    -0.06
     }}"></
    -0.06
    аков
    -0.06
    bearer
    -0.06
    umas
    -0.06
    POSITIVE LOGITS
     mitochondrial
    0.06
    .login
    0.06
     вокруг
    0.06
     desper
    0.06
    _my
    0.06
     oat
    0.06
    ‐‐
    0.06
     escorts
    0.06
     Captain
    0.06
     gé
    0.06
    Act Density 0.019%

    No Known Activations