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

    Neuronpedia

    INDEX
    Explanations

    seeking goals or knowledge

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     przetwarz
    0.37
    太太
    0.37
     milliseconds
    0.36
    メソッド
    0.36
    食品
    0.36
     অপারে
    0.35
    電話
    0.35
     alphan
    0.35
     ڈیٹا
    0.35
    高速
    0.34
    POSITIVE LOGITS
     adventurers
    0.60
     heroic
    0.59
     adventurer
    0.59
     heroism
    0.57
     hero
    0.54
     mercenary
    0.54
     heroes
    0.54
     adventure
    0.53
     mercenaries
    0.53
     exiled
    0.52
    Act Density 0.569%

    No Known Activations