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

    Neuronpedia

    INDEX
    Explanations

    you are a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     διαφο
    0.38
    Ꮵ
    0.37
     szabály
    0.37
     affez
    0.36
    ας
    0.36
     архіви
    0.36
    囪
    0.36
     аспек
    0.35
     создавать
    0.35
    沍
    0.34
    POSITIVE LOGITS
     writing
    0.33
     write
    0.32
     an
    0.31
    Writing
    0.31
    p
    0.31
    text
    0.30
    king
    0.30
     screenplay
    0.30
     लिखते
    0.30
     Seorang
    0.30
    Act Density 0.066%

    No Known Activations