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

    Neuronpedia

    INDEX
    Explanations

    time since

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     계속
    0.56
    一开始
    0.44
     semper
    0.42
     всегда
    0.42
     continue
    0.41
     continually
    0.39
     যতই
    0.38
     продовжу
    0.38
    不斷
    0.38
     எல்லாம்
    0.37
    POSITIVE LOGITS
     since
    1.36
     منذ
    1.24
    since
    1.21
     seit
    1.16
     sinds
    1.10
     Since
    1.09
     sejak
    1.08
    Since
    1.04
     depuis
    0.99
    以来
    0.95
    Act Density 0.011%

    No Known Activations