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

    Neuronpedia

    INDEX
    Explanations

    definitions or descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kuti
    0.24
    d
    0.24
       
    0.22
     kyr
    0.21
    etc
    0.21
     Klav
    0.21
     Wh
    0.20
     അടിസ്ഥാന
    0.20
    Qu
    0.19
    dtype
    0.19
    POSITIVE LOGITS
     자체
    0.24
     prowess
    0.23
    박
    0.23
     shenanigans
    0.23
    霽
    0.23
     itself
    0.23
     종류
    0.23
    बंदी
    0.22
    स्तर
    0.22
    ান্তে
    0.22
    Act Density 0.286%

    No Known Activations