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

    Neuronpedia

    INDEX
    Explanations

    change

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sheaf
    0.52
    pieceSelection
    0.51
     semisimple
    0.51
    ïdes
    0.50
     стрельца
    0.50
    ONEDB
    0.49
    셍
    0.48
     Цуки
    0.48
    allele
    0.47
    weist
    0.47
    POSITIVE LOGITS
    s
    0.52
    ,
    0.50
    í
    0.48
    ı
    0.47
    ll
    0.45
    ات
    0.45
    ة
    0.45
    Introducing
    0.45
    l
    0.45
    Government
    0.44
    Act Density 0.001%

    No Known Activations