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

    Neuronpedia

    INDEX
    Explanations

    was or were describing origins

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Currently
    0.54
    目前
    0.52
     сейчас
    0.52
     atualmente
    0.50
    Currently
    0.50
     현재
    0.49
     目前
    0.49
     obecnie
    0.49
     attualmente
    0.47
    ตอนนี้
    0.46
    POSITIVE LOGITS
     originally
    0.82
    originally
    0.67
     originalmente
    0.59
     instrumental
    0.55
     able
    0.54
     reportedly
    0.52
     ursprünglich
    0.49
     Originally
    0.49
    Originally
    0.48
     damals
    0.48
    Act Density 0.077%

    No Known Activations