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

    Neuronpedia

    INDEX
    Explanations

    how you/it works

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     chỉ
    0.40
    有很多
    0.36
    有一個
    0.35
     teníamos
    0.34
     ejemplos
    0.34
     hanya
    0.33
    有不少
    0.33
     duidelijk
    0.33
     Existe
    0.33
     only
    0.32
    POSITIVE LOGITS
     behave
    0.64
     behaves
    0.61
     interacts
    0.60
     behaved
    0.59
     relate
    0.58
     relates
    0.57
     fonctionne
    0.57
     differ
    0.55
    看待
    0.54
     fonctionnent
    0.54
    Act Density 0.095%

    No Known Activations