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

    Neuronpedia

    INDEX
    Explanations

    date

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Marseille
    -0.07
    urve
    -0.06
    Tiles
    -0.06
    553
    -0.06
     blown
    -0.06
     EIF
    -0.06
     proper
    -0.06
     Phạm
    -0.06
     Essay
    -0.06
     arada
    -0.06
    POSITIVE LOGITS
     이벤트
    0.07
    _dates
    0.07
     obsahuje
    0.07
    学习
    0.06
    .onclick
    0.06
     squir
    0.06
    .easy
    0.06
     QUI
    0.06
    locator
    0.06
    oga
    0.06
    Act Density 0.014%

    No Known Activations