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

    Neuronpedia

    INDEX
    Explanations

    say "int" or "uint"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    urtles
    -0.06
     herself
    -0.06
    -function
    -0.06
    =p
    -0.06
     Pump
    -0.06
    uits
    -0.06
    iterals
    -0.06
    =P
    -0.06
    ksen
    -0.05
     dataTable
    -0.05
    POSITIVE LOGITS
     InterruptedException
    0.07
    ทย
    0.06
     청
    0.06
    状況
    0.06
    xEF
    0.06
     tread
    0.06
     joe
    0.06
     забезпеч
    0.06
     두
    0.06
     Almanya
    0.06
    Act Density 0.004%

    No Known Activations