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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Archive
    -0.07
     Mata
    -0.07
     dicks
    -0.07
    ξύ
    -0.06
     polls
    -0.06
     Backpack
    -0.06
    Tube
    -0.06
    Fans
    -0.06
     Fans
    -0.06
    tro
    -0.06
    POSITIVE LOGITS
    (event
    0.07
     giorno
    0.06
    =db
    0.06
    -opt
    0.06
    .Note
    0.06
    ,on
    0.06
     FileStream
    0.06
     v
    0.06
    UnderTest
    0.06
     Wii
    0.06
    Act Density 0.002%

    No Known Activations