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

    Neuronpedia

    INDEX
    Explanations

    get

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Mouse
    -0.07
    สมเด
    -0.06
     Fully
    -0.06
    .Row
    -0.06
    警
    -0.06
     демон
    -0.06
     wol
    -0.06
    .Builder
    -0.06
    ”;
    -0.06
     king
    -0.06
    POSITIVE LOGITS
     인기글
    0.07
    wall
    0.07
    cpy
    0.06
    TableView
    0.06
    фф
    0.06
    }")↵
    0.06
     wissen
    0.06
    ,out
    0.06
    "+"
    0.06
    Seven
    0.06
    Act Density 0.003%

    No Known Activations