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

    Neuronpedia

    INDEX
    Explanations

    code parsing and regex

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    necklace
    0.92
    ᓇ
    0.90
    amiento
    0.88
     নুরুল
    0.85
    señ
    0.84
    ().__
    0.84
    pkl
    0.83
     विचारक
    0.81
    ip
    0.80
    .--
    0.79
    POSITIVE LOGITS
     ;
    1.31
    ;
    1.27
    ;")
    0.99
     ;\
    0.99
    ;"
    0.95
    ;<
    0.94
    ；
    0.92
     ؛
    0.89
    ;\
    0.89
     Gift
    0.88
    Act Density 0.108%

    No Known Activations