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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     repeal
    -0.07
     Million
    -0.07
     corrections
    -0.07
     Resident
    -0.07
    icers
    -0.07
     Spicer
    -0.06
     Relative
    -0.06
     squeezed
    -0.06
     prerequisites
    -0.06
     lords
    -0.06
    POSITIVE LOGITS
    ικοί
    0.07
    .menu
    0.07
    Nit
    0.07
     CWE
    0.07
    .pages
    0.06
    Ó
    0.06
    人的
    0.06
     FK
    0.06
    Wat
    0.06
     Ã
    0.06
    Act Density 0.190%

    No Known Activations