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

    Neuronpedia

    INDEX
    Explanations

    reading comprehension passages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    律
    0.39
     नोटबुक
    0.38
    ^{+}\
    0.37
    etted
    0.37
    烂
    0.37
     répét
    0.36
    ریف
    0.36
     भरपूर
    0.36
     phrase
    0.36
    ющими
    0.36
    POSITIVE LOGITS
     passage
    0.61
     passages
    0.56
     camping
    0.52
    passage
    0.51
     read
    0.50
     Passage
    0.49
     reading
    0.48
     Camping
    0.48
    छु
    0.45
    閲
    0.45
    Act Density 0.004%

    No Known Activations