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

    Neuronpedia

    INDEX
    Explanations

    social connections and networking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    agiarism
    0.44
     chromed
    0.41
    摘要
    0.38
     fichiers
    0.38
    kb
    0.37
     computes
    0.37
    metadata
    0.37
    精度
    0.37
     logiciel
    0.37
     kilobytes
    0.37
    POSITIVE LOGITS
     friendships
    1.11
    社交
    1.01
     social
    0.95
     친구
    0.94
     interpersonal
    0.93
     friendship
    0.93
     friends
    0.91
     социа
    0.89
     sociale
    0.88
     sociable
    0.88
    Act Density 0.332%

    No Known Activations