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

    Neuronpedia

    INDEX
    Explanations

    death sentence or threat

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ys
    0.62
     optimised
    0.60
    USE
    0.58
    트
    0.57
    Hz
    0.56
    eru
    0.55
     አገልግሎ
    0.55
     ສຳ
    0.55
    𒇽
    0.55
    DR
    0.55
    POSITIVE LOGITS
     death
    1.24
     muerte
    1.20
    death
    1.09
     Death
    1.06
     morte
    1.06
    Death
    1.02
    死
    0.98
    死的
    0.98
     مرگ
    0.93
     DEATH
    0.91
    Act Density 0.020%

    No Known Activations