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

    Neuronpedia

    INDEX
    Explanations

    until

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     আজকাল
    0.38
    এবার
    0.38
     এক্ষ
    0.34
     Forth
    0.33
    ार्थी
    0.33
     зараз
    0.33
    溇
    0.32
    蹩
    0.32
    ڈر
    0.31
     বর্তমানে
    0.31
    POSITIVE LOGITS
     until
    2.95
     hasta
    2.72
     até
    2.64
    until
    2.61
     jusqu
    2.53
    Until
    2.50
     Until
    2.48
     hingga
    2.42
    直到
    2.39
     sampai
    2.36
    Act Density 0.070%

    No Known Activations