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

    Neuronpedia

    INDEX
    Explanations

    risk, illness, death

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Bevölkerung
    0.49
     niñas
    0.45
     Adolescent
    0.45
     BuzzFeed
    0.45
     Metallica
    0.45
     TikTok
    0.44
     Adoles
    0.44
     Airbnb
    0.43
     किशोर
    0.43
     Kỳ
    0.43
    POSITIVE LOGITS
     overall
    0.54
    overall
    0.48
     deaths
    0.46
    events
    0.44
    all
    0.42
    event
    0.42
     incidence
    0.42
     manageable
    0.41
     complications
    0.41
     incidents
    0.41
    Act Density 0.021%

    No Known Activations