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

    Neuronpedia

    INDEX
    Explanations

    birth dates and ages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Sequelize
    0.38
     新
    0.37
     svjet
    0.37
     kosm
    0.36
    彻
    0.35
     Sequel
    0.35
     Senator
    0.35
     Snapshot
    0.35
    addTask
    0.35
     "{
    0.34
    POSITIVE LOGITS
     ଯ
    0.45
    ंदगी
    0.41
     cen
    0.41
    éta
    0.40
     років
    0.40
     Cen
    0.40
     sierpnia
    0.39
    मिन
    0.38
     אטאטורק
    0.38
     précise
    0.38
    Act Density 0.031%

    No Known Activations