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

    Neuronpedia

    INDEX
    Explanations

    contradiction/conflict

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     abound
    -0.07
    quality
    -0.07
     saúde
    -0.07
     waivers
    -0.07
    YES
    -0.06
    Vien
    -0.06
    овала
    -0.06
    .edit
    -0.06
     Franç
    -0.06
     شوند
    -0.06
    POSITIVE LOGITS
     tableLayoutPanel
    0.06
     principalTable
    0.06
     ilgi
    0.06
     PdfPCell
    0.06
    _bn
    0.06
    :#
    0.06
     tvrd
    0.06
    .Multi
    0.06
     способом
    0.06
    _whitespace
    0.06
    Act Density 0.013%

    No Known Activations