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

    Neuronpedia

    INDEX
    Explanations

    works as an occupation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vision
    0.36
     depicts
    0.36
     discord
    0.36
     comprises
    0.35
     timeless
    0.35
     frictionless
    0.35
     necessitates
    0.35
    គ្មាន
    0.34
     fragment
    0.34
     COMPLETE
    0.34
    POSITIVE LOGITS
     работал
    0.76
     trabajar
    0.73
     работать
    0.73
     arbeitete
    0.73
     lavorare
    0.72
     trabalhar
    0.72
     freelance
    0.71
     assistant
    0.71
     பணியாற்ற
    0.70
     consultant
    0.70
    Act Density 0.024%

    No Known Activations