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

    Neuronpedia

    INDEX
    Explanations

    types, numbers, database

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ظيف
    0.52
    Recommend
    0.47
     utilizados
    0.45
     tinham
    0.45
     mirip
    0.45
     poteva
    0.44
     tenían
    0.44
     utilisent
    0.44
    ob
    0.44
     estava
    0.44
    POSITIVE LOGITS
    Когда
    0.53
    ร
    0.49
    י
    0.48
    ВА
    0.46
     দেবী
    0.45
     सच्ची
    0.45
     Когда
    0.45
     жизни
    0.44
     строку
    0.44
     уг
    0.44
    Act Density 0.004%

    No Known Activations