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

    Neuronpedia

    INDEX
    Explanations

    books and publishers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    automate
    0.40
    MaskInto
    0.38
     Automation
    0.38
    encode
    0.37
    澪
    0.37
    watering
    0.37
    google
    0.36
     Datum
    0.36
     মোতাবেক
    0.36
    雁
    0.36
    POSITIVE LOGITS
     buk
    0.44
     saber
    0.40
     Кита
    0.40
     alph
    0.39
    ẵn
    0.39
     tyl
    0.38
     pasal
    0.37
     chuy
    0.37
     sau
    0.37
     ánh
    0.36
    Act Density 0.002%

    No Known Activations