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

    Neuronpedia

    INDEX
    Explanations

    colonists and colonies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Gil
    0.41
     Dies
    0.40
     উইকেট
    0.40
    Essential
    0.39
     Supports
    0.39
    ņu
    0.38
    Dies
    0.38
     бонусу
    0.38
    Helmet
    0.38
     speechSynthesis
    0.37
    POSITIVE LOGITS
     colonists
    0.54
     colonial
    0.51
     colonized
    0.51
     colonialism
    0.50
     colonies
    0.49
     (:
    0.48
     colony
    0.47
     colon
    0.46
     Colony
    0.45
    (':
    0.45
    Act Density 0.001%

    No Known Activations