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

    Neuronpedia

    INDEX
    Explanations

    team followed by player, lead, or achievements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    p
    0.71
    "
    0.65
     la
    0.64
     ofer
    0.63
     но
    0.61
    ка
    0.61
     indole
    0.59
    Є
    0.59
    of
    0.59
     condemn
    0.58
    POSITIVE LOGITS
     Team
    0.97
     équipes
    0.89
     팀
    0.88
    Team
    0.87
     équipe
    0.86
     टीम
    0.86
     equipes
    0.84
     ટીમ
    0.83
     TEAM
    0.82
     teamwork
    0.81
    Act Density 0.041%

    No Known Activations