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

    Neuronpedia

    INDEX
    Explanations

    references to societal norms and collective experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    everyday life

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     المعيارى
    -0.80
     ब्रेकडाउन
    -0.68
    findpost
    -0.65
    uxxxx
    -0.63
     للاسماء
    -0.62
     dieſes
    -0.62
    GEBURTSDATUM
    -0.60
     deſſen
    -0.60
     zuſammen
    -0.60
     erſt
    -0.59
    POSITIVE LOGITS
    Viitteet
    0.27
     آزم
    0.26
     kiệm
    0.25
     national
    0.25
     every
    0.25
     dreams
    0.25
     Tim
    0.23
     Min
    0.23
     dream
    0.22
     :
    0.22
    Act Density 0.088%

    No Known Activations