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

    Neuronpedia

    INDEX
    Explanations

    honor and celebration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     addictive
    0.48
     menus
    0.46
     aplicaciones
    0.45
     supon
    0.44
     zabez
    0.44
     aig
    0.43
     problème
    0.43
     sorpre
    0.42
     boxes
    0.42
     базы
    0.41
    POSITIVE LOGITS
     commemorating
    0.77
     기념
    0.74
    纪念
    0.71
     anniversary
    0.68
     celebrating
    0.64
     commemorate
    0.64
     annivers
    0.63
     commemoration
    0.61
     commemorates
    0.60
     martyrs
    0.60
    Act Density 0.049%

    No Known Activations