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

    Neuronpedia

    INDEX
    Explanations

    building and rebuilding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    وا
    0.53
    buscador
    0.51
    多久
    0.50
    ង្វ
    0.48
    出
    0.46
    quil
    0.45
    ка
    0.44
    ప్పు
    0.43
    هم
    0.42
    ukuran
    0.42
    POSITIVE LOGITS
    蓥
    0.44
    );//
    0.44
     Confucian
    0.44
    ̕
    0.43
     Literacy
    0.43
     Department
    0.43
     Volunteer
    0.42
     Education
    0.42
    খ্যার
    0.42
     那麼
    0.42
    Act Density 0.003%

    No Known Activations