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

    Neuronpedia

    INDEX
    Explanations

    if doing so

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     অবশ্য
    0.39
     നടത്തിയ
    0.37
    これで
    0.36
    ymin
    0.36
     zee
    0.36
    のが
    0.35
     وهنا
    0.35
    യിലെ
    0.34
    ateurs
    0.34
    ască
    0.33
    POSITIVE LOGITS
     so
    2.83
    so
    1.91
     So
    1.73
    如此
    1.71
    So
    1.68
     så
    1.65
     socalled
    1.64
    那么
    1.49
     так
    1.46
     soooo
    1.42
    Act Density 0.016%

    No Known Activations