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

    Neuronpedia

    INDEX
    Explanations

    choosing best option

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     contrace
    0.63
     copyright
    0.62
     কর্তৃক
    0.62
     typical
    0.61
    typical
    0.61
     coined
    0.61
    leen
    0.61
     conceived
    0.60
    conce
    0.60
     প্রণ
    0.60
    POSITIVE LOGITS
     escolher
    1.20
     выбира
    1.20
     scegliere
    1.17
     elegir
    1.17
     choisir
    1.17
     scegli
    1.16
     เลือก
    1.16
     pilih
    1.15
     escolha
    1.15
     look
    1.14
    Act Density 0.254%

    No Known Activations