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

    Neuronpedia

    INDEX
    Explanations

    this work paper research study

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     switches
    0.36
     массив
    0.35
     soundtracks
    0.34
     sw
    0.34
     versions
    0.33
     jawaban
    0.33
    Books
    0.33
     statues
    0.33
     mortgages
    0.33
     joueurs
    0.33
    POSITIVE LOGITS
    研究
    0.83
     research
    0.81
     연구
    0.78
     paper
    0.77
     penelitian
    0.77
     исследование
    0.75
     study
    0.75
    research
    0.72
     onderzoek
    0.69
    paper
    0.68
    Act Density 0.013%

    No Known Activations