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

    Neuronpedia

    INDEX
    Explanations

    memories of bygone times

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     derzeit
    0.77
     recent
    0.75
     currently
    0.75
    目前
    0.73
     আপাতত
    0.73
     récente
    0.73
     attualmente
    0.71
    recent
    0.68
    これまで
    0.68
     senaste
    0.68
    POSITIVE LOGITS
    当时
    1.99
    当时的
    1.97
    當時
    1.93
     damal
    1.93
     damals
    1.92
     당시
    1.78
    当時の
    1.77
    当時
    1.73
     তখনকার
    1.63
    那时候
    1.58
    Act Density 0.006%

    No Known Activations