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

    Neuronpedia

    INDEX
    Explanations

    promoting justice and a better future

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Productivity
    0.46
    career
    0.43
     Carrick
    0.43
     Career
    0.42
     productividad
    0.42
     Performance
    0.42
    Career
    0.42
     करियर
    0.41
    productivity
    0.41
     Output
    0.40
    POSITIVE LOGITS
     justice
    1.01
    justice
    0.80
     justicia
    0.77
     fairer
    0.76
     equitable
    0.75
     safer
    0.74
     justiça
    0.73
     happier
    0.72
     better
    0.71
     truly
    0.71
    Act Density 0.009%

    No Known Activations