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

    Neuronpedia

    INDEX
    Explanations

    spending time on activities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     semangat
    0.78
     memerlukan
    0.76
    Through
    0.73
     Through
    0.72
     käyttö
    0.72
     zmienia
    0.71
     हानि
    0.71
     принимает
    0.71
     doloribus
    0.70
     wszyst
    0.70
    POSITIVE LOGITS
     lobbying
    0.95
     researching
    0.93
     arguing
    0.89
    研发
    0.88
     searching
    0.87
     frivol
    0.87
     explaining
    0.86
     lobbyists
    0.85
     debating
    0.84
     devoted
    0.82
    Act Density 0.087%

    No Known Activations