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

    Neuronpedia

    INDEX
    Explanations

    for a long time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Tomorrow
    0.42
    ിച്ച
    0.41
    未来的
    0.40
     მაშინ
    0.40
     another
    0.39
     cuando
    0.38
    tomorrow
    0.38
    嘿
    0.38
     Another
    0.37
     tomorrow
    0.37
    POSITIVE LOGITS
    ัตว์
    0.46
     આનંદ
    0.45
     länge
    0.41
    しばらく
    0.40
     numbering
    0.38
     mathematician
    0.37
     dude
    0.36
    ጀም
    0.36
     mathematicians
    0.36
    所に
    0.36
    Act Density 0.001%

    No Known Activations