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

    Neuronpedia

    INDEX
    Explanations

    years or decades

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     γιατί
    0.35
     omdat
    0.33
     kerana
    0.33
     waardoor
    0.31
     ดังนั้น
    0.31
     거고
    0.30
     کیونکہ
    0.30
     wobei
    0.30
    чие
    0.30
    是我们
    0.30
    POSITIVE LOGITS
    ،
    0.38
    ,
    0.38
    ,(
    0.33
    ,.
    0.31
     ,
    0.30
    ,,
    0.30
    ，
    0.29
    ,_
    0.29
    ͕
    0.28
     there
    0.28
    Act Density 0.032%

    No Known Activations