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

    Neuronpedia

    INDEX
    Explanations

    say "parenthesis"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     RES
    -0.07
     BAL
    -0.07
     fetched
    -0.07
     Auf
    -0.07
    .edu
    -0.07
     mein
    -0.07
    ,cv
    -0.07
    プリ
    -0.07
     Cheers
    -0.07
     BUS
    -0.07
    POSITIVE LOGITS
     النقد
    0.08
     ngại
    0.07
    科幻
    0.07
     fermentation
    0.07
    TextLabel
    0.07
    :')↵
    0.07
    药业
    0.07
     QStringList
    0.07
    Playable
    0.07
    .xrTableCell
    0.07
    Act Density 0.003%

    No Known Activations