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

    Neuronpedia

    INDEX
    Explanations

    offers and expectations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fonctionnent
    0.35
     BULLETIN
    0.34
     anyag
    0.33
     jambes
    0.33
     absent
    0.32
     পদ্ধতি
    0.32
    物体
    0.32
     अर्थात्
    0.32
    ସ୍
    0.32
    ENGLISH
    0.32
    POSITIVE LOGITS
     menawarkan
    0.41
     offers
    0.41
    Offers
    0.40
    offers
    0.39
    awarkan
    0.35
    Dar
    0.34
     Offers
    0.34
    Karo
    0.34
    Offer
    0.33
     oferecer
    0.33
    Act Density 0.000%

    No Known Activations