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

    Neuronpedia

    INDEX
    Explanations

    making official declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hành
    0.43
    表现
    0.42
     persuasion
    0.42
     menggambarkan
    0.40
     குறிப்பி
    0.40
    表現
    0.39
     roug
    0.39
     Beschreibung
    0.39
     okre
    0.38
     prototyping
    0.38
    POSITIVE LOGITS
     allegiance
    0.82
     loudly
    0.70
     declare
    0.68
     intentions
    0.63
     aloud
    0.59
     readiness
    0.59
    宣言
    0.59
    declare
    0.58
     candidacy
    0.58
     declarations
    0.58
    Act Density 0.009%

    No Known Activations