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

    Neuronpedia

    INDEX
    Explanations

    personal statements and references to time

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cans
    -0.94
    als
    -0.94
    ths
    -0.92
    tols
    -0.90
    bergs
    -0.88
    eds
    -0.88
    alds
    -0.88
    Zs
    -0.86
    rds
    -0.86
    ets
    -0.86
    POSITIVE LOGITS
    yarnpkg
    0.38
     autorytatywna
    0.36
    Rhestr
    0.35
     préoccup
    0.34
    ėtų
    0.34
    leneck
    0.34
    liferay
    0.33
    balleur
    0.33
    ürn
    0.32
     bénéfices
    0.32
    Act Density 46.012%

    No Known Activations