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

    Neuronpedia

    INDEX
    Explanations

    concerned about

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     anxieties
    0.52
     উদ্বেগ
    0.44
     نگرانی
    0.43
     anxiety
    0.42
     uncertainty
    0.42
     preocupaciones
    0.41
    ۖ
    0.41
     worries
    0.40
     concerns
    0.39
    Especially
    0.38
    POSITIVE LOGITS
    oría
    0.46
    enery
    0.43
    有害
    0.41
    雵
    0.41
     For
    0.40
    gutter
    0.40
     Turbo
    0.39
    ecs
    0.38
     своей
    0.38
    reset
    0.38
    Act Density 0.001%

    No Known Activations