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

    Neuronpedia

    INDEX
    Explanations

    professionals and their names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    เป็น
    0.38
    下記の
    0.38
    backend
    0.38
    frontend
    0.38
    termin
    0.37
    action
    0.37
    skip
    0.37
    ｉ
    0.36
    default
    0.36
    цион
    0.36
    POSITIVE LOGITS
    ,
    0.57
     extraordinaire
    0.53
    യായ
    0.48
    ،
    0.48
     وم
    0.43
     llamado
    0.43
     అయిన
    0.43
     sekaligus
    0.43
     Лу
    0.43
     called
    0.42
    Act Density 0.006%

    No Known Activations