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

    Neuronpedia

    INDEX
    Explanations

    Programming/tech (non-English)

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     admit
    -0.06
     '↵
    -0.06
     Where
    -0.06
    ("\"
    -0.06
     hole
    -0.06
     ngọt
    -0.06
     paradox
    -0.06
     sabe
    -0.06
     Если
    -0.06
    Where
    -0.06
    POSITIVE LOGITS
    وان
    0.07
    atoi
    0.07
     sola
    0.07
     UINavigationController
    0.07
    ními
    0.07
    .LINE
    0.07
    ικής
    0.07
    wolf
    0.07
    HOUSE
    0.07
     mercenaries
    0.06
    Act Density 0.044%

    No Known Activations