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

    Neuronpedia

    INDEX
    Explanations

    military medals and insignia

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     موت
    0.41
     પોસ્ટ
    0.40
     چاہے
    0.40
     Plots
    0.40
    胙
    0.40
     honours
    0.39
    POST
    0.39
     Medal
    0.38
     perintah
    0.38
    Plots
    0.38
    POSITIVE LOGITS
     arrowhead
    0.57
     ribbons
    0.55
     campaign
    0.51
     Good
    0.50
    Good
    0.50
     cluster
    0.50
     streamers
    0.50
     arrow
    0.49
     device
    0.49
    Cluster
    0.49
    Act Density 0.002%

    No Known Activations