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

    Neuronpedia

    INDEX
    Explanations

    in or within a context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    สำหรับ
    0.38
     something
    0.37
    with
    0.36
     itself
    0.36
    ena
    0.36
     with
    0.35
    是一个
    0.35
     für
    0.35
     for
    0.34
    ination
    0.34
    POSITIVE LOGITS
     jotka
    0.46
     kteří
    0.45
     którzy
    0.45
     kurie
    0.44
     ktorí
    0.41
     gleiche
    0.38
     alrededores
    0.38
     الذين
    0.38
     kiuj
    0.38
     цієї
    0.38
    Act Density 0.151%

    No Known Activations