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

    Neuronpedia

    INDEX
    Explanations

    LLaMA

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ure
    1.15
    age
    1.12
    +",
    1.07
    على
    1.06
    上演
    1.06
    ول
    1.05
    👵
    1.04
     endocr
    1.02
    trashItem
    1.01
     kil
    0.99
    POSITIVE LOGITS
    ي
    1.86
    ি
    1.58
    Т
    1.39
    ד
    1.36
     Fakat
    1.33
    驛
    1.33
     oración
    1.30
    ाई
    1.30
    سي
    1.30
    했으며
    1.28
    Act Density 0.037%

    No Known Activations