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

    Neuronpedia

    INDEX
    Explanations

    aur

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Churchill
    -0.08
     paradox
    -0.06
     snippet
    -0.06
     casual
    -0.06
    PAIR
    -0.06
    .XtraPrinting
    -0.06
    :NS
    -0.06
     дозвол
    -0.06
     fazla
    -0.06
    yellow
    -0.06
    POSITIVE LOGITS
    今天
    0.07
     nå
    0.07
     ahora
    0.07
     Moments
    0.07
    _Create
    0.07
    imdi
    0.07
    ，现在
    0.07
    今
    0.06
    _corner
    0.06
     agora
    0.06
    Act Density 0.031%

    No Known Activations