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

    Neuronpedia

    INDEX
    Explanations

    SEO, Publications, Hernandez

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ogrod
    0.45
    當地
    0.45
     civile
    0.43
     tuin
    0.42
     wilt
    0.41
     semoga
    0.41
     stupe
    0.41
     honti
    0.40
    当地
    0.40
    ⑮
    0.40
    POSITIVE LOGITS
    ेड
    0.42
    Publish
    0.40
     Publications
    0.40
    SEO
    0.40
    ֻ
    0.40
    andez
    0.38
    ·
    0.38
    ઢી
    0.37
    arus
    0.37
    seo
    0.37
    Act Density 0.024%

    No Known Activations