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

    Neuronpedia

    INDEX
    Explanations

    child labor and early work

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     narciss
    0.45
    shower
    0.44
     hyster
    0.42
    population
    0.41
    wives
    0.41
     creamy
    0.41
     immunology
    0.41
    人口
    0.40
     cis
    0.39
    fashion
    0.39
    POSITIVE LOGITS
     apprentices
    0.65
     apprenticeship
    0.64
     apprentice
    0.61
     apprent
    0.61
     Apprentices
    0.59
    少年
    0.58
     aprendiz
    0.58
     коммер
    0.55
     underage
    0.55
     autod
    0.55
    Act Density 0.026%

    No Known Activations