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

    Neuronpedia

    INDEX
    Explanations

    one or each instance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    groups
    0.46
     Teams
    0.46
     arrays
    0.44
    Teams
    0.44
    teams
    0.42
     generically
    0.42
     equipos
    0.41
     teams
    0.41
     ecosystems
    0.39
     optionally
    0.39
    POSITIVE LOGITS
     member
    0.81
    成员
    0.80
     members
    0.75
     सदस्य
    0.74
    成員
    0.74
     član
    0.69
     멤버
    0.68
     člen
    0.66
     anggota
    0.65
    member
    0.64
    Act Density 0.016%

    No Known Activations