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

    Neuronpedia

    INDEX
    Explanations

    durability and exceptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    րան
    0.51
    ETARY
    0.50
    かせ
    0.48
    racial
    0.48
    ത്തിക
    0.48
    %/
    0.47
    getPassword
    0.47
    tidal
    0.47
    চরা
    0.46
    ꫝ
    0.46
    POSITIVE LOGITS
     عصر
    0.45
     consulted
    0.42
     جزء
    0.42
    Va
    0.41
     begann
    0.41
     ترك
    0.40
     систе
    0.40
     кру
    0.40
    lega
    0.40
     الرب
    0.39
    Act Density 0.002%

    No Known Activations