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

    Neuronpedia

    INDEX
    Explanations

    episode, guest interviews, lead announcements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     stupidity
    0.58
     stupid
    0.56
     enemies
    0.50
     primitive
    0.47
     android
    0.46
     dinheiro
    0.46
     unstable
    0.46
     necrosis
    0.46
     corrupted
    0.46
     swallowing
    0.46
    POSITIVE LOGITS
    🎙
    0.65
     интервью
    0.64
     экспер
    0.63
     webinar
    0.62
    Executive
    0.61
     nuestra
    0.61
     Executive
    0.60
    Interview
    0.59
     🎉
    0.59
     Outreach
    0.57
    Act Density 0.023%

    No Known Activations