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

    Neuronpedia

    INDEX
    Explanations

    ethical principles and social sciences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     skills
    0.75
     habilidades
    0.65
    skills
    0.64
     Skills
    0.60
     навыки
    0.59
     skill
    0.57
     teen
    0.54
     teens
    0.54
    技能
    0.52
    Skills
    0.52
    POSITIVE LOGITS
     ética
    0.54
     ethically
    0.50
     глоба
    0.48
     collaborate
    0.42
     озна
    0.42
     ét
    0.42
    ">[
    0.41
     comunicar
    0.40
     Ethics
    0.39
    Ethics
    0.39
    Act Density 0.006%

    No Known Activations