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

    Neuronpedia

    INDEX
    Explanations

    actions followed by context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Start
    0.54
    Finish
    0.53
    Sock
    0.53
    Location
    0.51
    沺
    0.50
    Phys
    0.50
     start
    0.49
    ldon
    0.49
     بیت
    0.49
    arid
    0.49
    POSITIVE LOGITS
     würde
    0.59
     vyš
    0.58
     гораздо
    0.57
     glum
    0.57
     maravilh
    0.56
     प्रतिभाशाली
    0.55
     —
    0.55
     thấy
    0.55
     nghiên
    0.55
     nemá
    0.55
    Act Density 0.073%

    No Known Activations