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

    Neuronpedia

    INDEX
    Explanations

    economic or technical growth

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PopupButton
    0.39
     #-
    0.37
     idha
    0.36
     referees
    0.36
     typing
    0.36
    wehr
    0.36
     Fiziki
    0.36
     alterna
    0.36
     প্রবন্ধে
    0.35
     vade
    0.35
    POSITIVE LOGITS
     bordered
    0.41
     stabilizes
    0.40
     सीमा
    0.39
    爻
    0.39
     eleven
    0.38
     stabilize
    0.38
     stabilizing
    0.38
     recovering
    0.37
     disappoint
    0.37
     delim
    0.37
    Act Density 0.001%

    No Known Activations