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

    Neuronpedia

    INDEX
    Explanations

    months

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     extinction
    -0.07
     Curso
    -0.06
    menus
    -0.06
    _Find
    -0.06
    _CRC
    -0.06
    蔌
    -0.06
     telling
    -0.06
     Yin
    -0.06
    _modify
    -0.06
    ,key
    -0.06
    POSITIVE LOGITS
     истор
    0.07
    Liverpool
    0.07
    Hora
    0.07
     Currently
    0.07
    星级酒店
    0.07
     infrastructure
    0.07
    Go
    0.06
    了一口气
    0.06
     сайте
    0.06
    -depth
    0.06
    Act Density 0.003%

    No Known Activations