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

    Neuronpedia

    INDEX
    Explanations

    Fin

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     crosses
    -0.07
    <object
    -0.07
    unning
    -0.07
     postpone
    -0.06
     Daly
    -0.06
     •
    -0.06
    尼亚
    -0.06
     HBO
    -0.06
    壁
    -0.06
    .ST
    -0.06
    POSITIVE LOGITS
    xAC
    0.07
    MainWindow
    0.06
    飲
    0.06
     durumunda
    0.06
    ">'.
    0.06
     кли
    0.06
     Bureau
    0.06
     использ
    0.06
    ケット
    0.06
    /interface
    0.06
    Act Density 0.214%

    No Known Activations