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

    Neuronpedia

    INDEX
    Explanations

    Sur + positive tokens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gắng
    0.43
    讪
    0.40
    ெட்
    0.39
    ریٹر
    0.39
    呵
    0.39
     Jalis
    0.38
    ＼
    0.38
     біль
    0.38
    esinde
    0.37
    鎮
    0.37
    POSITIVE LOGITS
    Sur
    0.90
     sur
    0.85
     Sur
    0.81
    sur
    0.79
     SUR
    0.73
    SUR
    0.66
    Surf
    0.57
    surf
    0.55
     Surrey
    0.54
     surrendered
    0.52
    Act Density 0.010%

    No Known Activations