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

    Neuronpedia

    INDEX
    Explanations

    Altruism

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     antider
    0.57
     моделей
    0.54
    增大
    0.54
     palmit
    0.52
     Erin
    0.51
     lesqu
    0.50
     aprendido
    0.50
     😏
    0.50
     dígitos
    0.50
     இடங்களில்
    0.50
    POSITIVE LOGITS
    на
    0.56
    Department
    0.55
    ุ
    0.48
    logger
    0.48
    참
    0.48
    old
    0.48
    you
    0.47
    Middleware
    0.46
    oju
    0.45
    ぞ
    0.45
    Act Density 0.000%

    No Known Activations