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

    Neuronpedia

    INDEX
    Explanations

    time management

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     encycl
    0.39
     encoder
    0.38
     traversed
    0.38
     bootstrap
    0.37
     ${{
    0.37
     faint
    0.36
     pions
    0.36
     twist
    0.35
     polymorphism
    0.35
    td
    0.35
    POSITIVE LOGITS
     시간을
    1.10
     time
    1.09
    時間
    1.08
    時間を
    1.08
     وقت
    1.01
    時間は
    1.00
    时间
    1.00
    시간
    1.00
     시간
    0.98
     tiempo
    0.95
    Act Density 0.072%

    No Known Activations