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

    Neuronpedia

    INDEX
    Explanations

    perceived relationships between social factors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ormous
    0.44
    Cryptography
    0.43
    약을
    0.42
    导弹
    0.41
    诞
    0.41
    Trains
    0.40
    炀
    0.40
    皤
    0.40
    硬盘
    0.40
    Everyone
    0.39
    POSITIVE LOGITS
     perceived
    1.20
     perceptions
    1.04
     attitudes
    0.94
     satisfaction
    0.90
     Attitudes
    0.88
     percep
    0.84
     perception
    0.84
     perceive
    0.80
     percib
    0.80
     perceiving
    0.79
    Act Density 0.025%

    No Known Activations