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

    Neuronpedia

    INDEX
    Explanations

    table headers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     retroactive
    0.44
     entrop
    0.43
     Gayatri
    0.40
    𐰑
    0.40
    rophication
    0.39
     espero
    0.39
     dizendo
    0.38
    resourceUrl
    0.38
     Katha
    0.38
     epig
    0.37
    POSITIVE LOGITS
    시
    0.40
     जितने
    0.39
    Ch
    0.38
    새
    0.37
    口罩
    0.36
    왠
    0.36
    ziemy
    0.35
    सूस
    0.35
    serif
    0.35
     Unite
    0.35
    Act Density 0.027%

    No Known Activations