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

    Neuronpedia

    INDEX
    Explanations

    work on or with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    3
    0.63
    5
    0.63
    4
    0.59
    7
    0.51
    it
    0.49
    6
    0.48
    re
    0.48
    ai
    0.47
    8
    0.47
    9
    0.46
    POSITIVE LOGITS
     trabalhando
    0.55
     Working
    0.54
     lavorare
    0.51
    Working
    0.49
     Work
    0.48
     duro
    0.47
     WORK
    0.47
     trabajar
    0.47
     работой
    0.46
     treball
    0.46
    Act Density 0.071%

    No Known Activations