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

    Neuronpedia

    INDEX
    Explanations

    defect

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     выполнить
    -0.09
     decreases
    -0.08
     hoo
    -0.08
     cunn
    -0.08
    ggy
    -0.08
     تنظيف
    -0.08
     सफ
    -0.08
     vlak
    -0.08
     centimeters
    -0.08
     Netto
    -0.08
    POSITIVE LOGITS
    connector
    0.08
    Analyzer
    0.08
    严重
    0.08
     gesammelt
    0.07
    Table
    0.07
    Connector
    0.07
     gestor
    0.07
    系统
    0.07
    _connector
    0.07
    Reporter
    0.07
    Act Density 0.006%

    No Known Activations