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

    Neuronpedia

    INDEX
    Explanations

    meeting to order

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     trivia
    0.28
     Utd
    0.27
     sky
    0.27
     gavel
    0.27
    spel
    0.26
    atsch
    0.26
    ehle
    0.26
     rhetoric
    0.26
     notion
    0.25
    ofsky
    0.25
    POSITIVE LOGITS
    體
    0.27
    Пер
    0.26
    قد
    0.26
     هن
    0.26
     ಎಂದ
    0.26
    接
    0.26
     стане
    0.25
     கைது
    0.25
    親
    0.25
    З
    0.24
    Act Density 0.279%

    No Known Activations