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

    Neuronpedia

    INDEX
    Explanations

    describes how something is or functions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Atau
    0.69
     것에
    0.68
     অথবা
    0.67
     طرف
    0.66
     şeyi
    0.65
    或者
    0.65
     или
    0.65
     或者
    0.62
     nebo
    0.62
     voluntad
    0.62
    POSITIVE LOGITS
     primarily
    0.74
     debuted
    0.70
     mainly
    0.68
     shorten
    0.68
     originated
    0.65
     significantly
    0.64
     মূলত
    0.64
     essentially
    0.64
     provide
    0.64
     pioneered
    0.64
    Act Density 0.358%

    No Known Activations