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

    Neuronpedia

    INDEX
    Explanations

    offering solutions and suggestions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pih
    0.73
     Affect
    0.72
     stigmat
    0.71
     toug
    0.71
     ශ
    0.70
     communicative
    0.70
     जागरूकता
    0.70
    парта
    0.69
     overwritten
    0.69
     prejudices
    0.69
    POSITIVE LOGITS
     offer
    1.37
     Offer
    1.36
    Offer
    1.36
     offers
    1.18
     offered
    1.17
     offering
    1.13
    offer
    1.12
     پیشنهاد
    1.12
     Offers
    1.11
    Offers
    1.08
    Act Density 0.211%

    No Known Activations