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

    Neuronpedia

    INDEX
    Explanations

    possessive relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     manglid
    0.38
     verfügt
    0.36
    পিং
    0.36
    addItem
    0.35
     একটি
    0.34
     ponctuées
    0.33
     ponctué
    0.33
     gaat
    0.32
     comienza
    0.32
     wirkt
    0.32
    POSITIVE LOGITS
     colleagues
    0.66
     fellow
    0.65
     friends
    0.64
     neighbours
    0.64
     contemporaries
    0.63
     partners
    0.62
     neighbors
    0.61
     peers
    0.61
     brethren
    0.60
     partner
    0.59
    Act Density 0.087%

    No Known Activations