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

    Neuronpedia

    INDEX
    Explanations

    loading libraries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     কোথাও
    0.39
     así
    0.37
    いただけ
    0.37
    reversed
    0.36
    ý
    0.35
    目的是
    0.35
     aix
    0.35
     ."
    0.35
     irgendwo
    0.35
     protagonisti
    0.34
    POSITIVE LOGITS
     सोशल
    0.50
     먼저
    0.46
     Biblioteca
    0.44
    共通
    0.43
    getServer
    0.42
     redire
    0.42
     Libraries
    0.42
     administrative
    0.41
     Administrative
    0.41
     보안
    0.41
    Act Density 0.003%

    No Known Activations