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

    Neuronpedia

    INDEX
    Explanations

    .com websites

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    備考
    0.38
    ZU
    0.36
    েলে
    0.36
    చర్
    0.35
    ধানা
    0.34
    ኪያ
    0.34
    Soda
    0.34
    毀
    0.33
    恤
    0.33
    શ્
    0.32
    POSITIVE LOGITS
    Therefore
    0.42
    _
    0.42
     Katherine
    0.39
     aforementioned
    0.39
     Teich
    0.37
     Portanto
    0.37
     Therefore
    0.36
     Ultimately
    0.36
     nên
    0.35
    লস
    0.35
    Act Density 0.018%

    No Known Activations