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

    Neuronpedia

    INDEX
    Explanations

    assuming office on dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    到时候
    0.39
    待
    0.37
    l
    0.34
    ards
    0.34
     अगला
    0.34
    cheduling
    0.33
    ˜</
    0.33
     अगली
    0.33
    隐藏
    0.33
    producing
    0.33
    POSITIVE LOGITS
     sejak
    0.72
     began
    0.70
     récente
    0.68
     started
    0.67
     منذ
    0.67
    Started
    0.65
     недавно
    0.65
     Started
    0.64
    自从
    0.63
    始めた
    0.63
    Act Density 0.055%

    No Known Activations