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

    Neuronpedia

    INDEX
    Explanations

    term or duration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     étages
    0.72
    mel
    0.66
     surgir
    0.65
     Mel
    0.64
     élabor
    0.64
    ൊരു
    0.62
    av
    0.61
    窘
    0.60
    Mel
    0.59
    下一步
    0.58
    POSITIVE LOGITS
     tenure
    2.06
     reign
    1.64
     stint
    1.63
     कार्यकाल
    1.58
     Tenure
    1.53
     пребы
    1.49
     stay
    1.47
     stints
    1.40
    期间
    1.39
    期間
    1.35
    Act Density 0.103%

    No Known Activations