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

    Neuronpedia

    INDEX
    Explanations

    large language model

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     multiplets
    0.38
     могу
    0.37
    这将
    0.37
    URNIZ
    0.36
    Hepin
    0.36
    したいと思います
    0.36
    ᱡ
    0.35
    METAL
    0.35
     বৎসর
    0.35
    相關
    0.35
    POSITIVE LOGITS
     www
    0.41
     the
    0.40
    www
    0.40
     FAQ
    0.37
     jednoduch
    0.36
     website
    0.34
     ethnographic
    0.33
     https
    0.33
     eponymous
    0.33
     [
    0.33
    Act Density 0.070%

    No Known Activations