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

    Neuronpedia

    INDEX
    Explanations

    projects and team roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mencegah
    0.70
     corretamente
    0.68
     phù
    0.67
     правильно
    0.66
     authorizes
    0.63
     adequada
    0.63
     допусти
    0.62
     eliminates
    0.61
     unauthorized
    0.59
     avoids
    0.59
    POSITIVE LOGITS
    projects
    0.86
     Projects
    0.84
    Team
    0.81
    Projects
    0.81
     Projekte
    0.80
     projects
    0.79
     exciting
    0.77
     팀
    0.76
     teamwork
    0.75
     team
    0.73
    Act Density 0.403%

    No Known Activations