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

    Neuronpedia

    INDEX
    Explanations

    section headings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     jab
    0.95
     tutaj
    0.90
     tr
    0.89
     mascot
    0.88
     king
    0.87
     purity
    0.87
     존재
    0.86
    存在
    0.85
     id
    0.84
     kus
    0.84
    POSITIVE LOGITS
     appendices
    1.72
     Appendix
    1.71
     appendix
    1.58
    Concluding
    1.54
    Appendix
    1.53
     Kapitel
    1.47
     chapters
    1.46
    appendix
    1.46
     Chương
    1.44
     chapter
    1.44
    Act Density 0.162%

    No Known Activations