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

    Neuronpedia

    INDEX
    Explanations

    starting withincharacterizing cystsIts purpose

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Decoration
    0.40
    pos
    0.38
     pos
    0.38
     Inst
    0.37
     ganz
    0.37
     Obviously
    0.37
     Обра
    0.37
    */)
    0.37
     Supra
    0.37
     Decre
    0.36
    POSITIVE LOGITS
    評價
    0.45
    ุต
    0.42
    ጽ
    0.40
     backed
    0.38
    ਝ
    0.38
     წ
    0.38
     murdered
    0.38
    یسر
    0.38
    スキル
    0.38
     rog
    0.37
    Act Density 0.000%

    No Known Activations