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

    Neuronpedia

    INDEX
    Explanations

    done

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     EDM
    -0.06
    .Percent
    -0.06
     Moody
    -0.06
    ыт
    -0.06
    EQUAL
    -0.06
     olan
    -0.05
     Âu
    -0.05
    developer
    -0.05
    ARI
    -0.05
     Kohana
    -0.05
    POSITIVE LOGITS
     máximo
    0.07
     approx
    0.07
     soubor
    0.07
     twelve
    0.07
     accommodate
    0.07
     треба
    0.07
     hamburger
    0.06
     harm
    0.06
     scipy
    0.06
     최신
    0.06
    Act Density 0.021%

    No Known Activations