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

    Neuronpedia

    INDEX
    Explanations

    heroic heroism heroes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    紊
    0.54
     Secrets
    0.43
     encro
    0.42
     জীববিজ্ঞান
    0.42
     secrets
    0.42
    箖
    0.40
     مرض
    0.40
    CreateInfo
    0.40
     Crib
    0.40
    Secrets
    0.39
    POSITIVE LOGITS
     heroism
    2.45
     heroic
    2.39
     hero
    2.08
     heroes
    2.06
    英雄
    1.99
     héro
    1.87
     bravery
    1.82
     геро
    1.81
     герой
    1.81
     герои
    1.78
    Act Density 0.018%

    No Known Activations