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

    Neuronpedia

    INDEX
    Explanations

    hard work

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Work
    0.80
     Work
    0.77
     WORK
    0.64
    WORKS
    0.55
     workday
    0.52
     업무
    0.52
     trabajos
    0.51
    WORK
    0.50
     Werk
    0.50
     work
    0.50
    POSITIVE LOGITS
     graft
    0.55
     Graft
    0.51
     grafted
    0.45
     GRA
    0.44
     gra
    0.41
     determinants
    0.41
     grafting
    0.40
     grafts
    0.40
    PARATION
    0.40
     word
    0.39
    Act Density 0.003%

    No Known Activations