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

    Neuronpedia

    INDEX
    Explanations

    centered

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ɵ
    -0.07
    jdbc
    -0.07
    πού
    -0.07
    ิค
    -0.06
    utor
    -0.06
    uropean
    -0.06
    인이
    -0.06
     wor
    -0.06
     ETH
    -0.06
     ấn
    -0.06
    POSITIVE LOGITS
     Зем
    0.07
     Hearing
    0.07
     Neural
    0.07
     Removing
    0.06
    .Remove
    0.06
     Flex
    0.06
     casos
    0.06
     draggable
    0.06
    Active
    0.06
     Foundations
    0.06
    Act Density 0.385%

    No Known Activations