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

    Neuronpedia

    INDEX
    Explanations

    awareness

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Secara
    0.35
     bont
    0.34
    \/
    0.34
     monstros
    0.33
     rusak
    0.33
     bonheur
    0.33
     Damit
    0.33
    靡
    0.33
     brackets
    0.32
     incorrectly
    0.32
    POSITIVE LOGITS
     mindful
    1.18
     cautious
    1.09
     attentive
    1.09
     vigilant
    1.08
     patient
    1.03
     diligent
    1.03
     proactive
    1.00
     thoughtful
    0.99
     aware
    0.98
     cognizant
    0.98
    Act Density 0.378%

    No Known Activations