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

    Neuronpedia

    INDEX
    Explanations

    news article about space

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     aliqu
    0.39
     भागों
    0.37
     서비스
    0.36
     시스템
    0.35
     항상
    0.35
     especificar
    0.35
     사용할
    0.35
     variabile
    0.35
     utilisé
    0.35
     가지고
    0.34
    POSITIVE LOGITS
     debunk
    0.51
     Journalist
    0.47
    blog
    0.46
    news
    0.46
     journalist
    0.46
     newsletter
    0.46
     racconto
    0.46
     Huffington
    0.46
     blog
    0.45
    article
    0.45
    Act Density 0.229%

    No Known Activations