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

    Neuronpedia

    INDEX
    Explanations

    instructing or informing groups

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Many
    0.39
    私は
    0.38
    আমি
    0.36
     আমি
    0.36
    អំ
    0.35
     நானும்
    0.35
    我也是
    0.34
     저는
    0.34
     मैंने
    0.33
    我很
    0.33
    POSITIVE LOGITS
     everyone
    0.74
    大家
    0.65
     participants
    0.59
    人們
    0.59
    人们
    0.58
     readers
    0.57
     people
    0.56
    everyone
    0.55
     iedereen
    0.55
     us
    0.54
    Act Density 0.022%

    No Known Activations