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

    Neuronpedia

    INDEX
    Explanations

    following specific words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     писать
    0.50
    preparing
    0.47
    󰡔
    0.47
    ﭥ
    0.47
    サスカ
    0.46
    Minn
    0.46
    Islamic
    0.46
    Raster
    0.46
    WRAP
    0.46
    ureshi
    0.46
    POSITIVE LOGITS
     Platforms
    0.45
     Platform
    0.43
    ungk
    0.41
     Foods
    0.39
     që
    0.39
     Development
    0.39
     Depression
    0.38
     Forschungs
    0.37
     Est
    0.37
     Stud
    0.37
    Act Density 0.000%

    No Known Activations