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

    Neuronpedia

    INDEX
    Explanations

    code variable assignments and list manipulation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    性和
    0.36
    ل
    0.32
    いたり
    0.30
    steroidal
    0.29
    ötzlich
    0.29
    ₂+
    0.29
    Ň
    0.28
    Church
    0.28
     মিলিয়ন
    0.27
    بول
    0.27
    POSITIVE LOGITS
    ，
    0.32
     is
    0.32
     \
    0.31
     =
    0.28
     whatnot
    0.26
     ==
    0.26
     was
    0.25
     isn
    0.24
     ,
    0.24
    ;
    0.24
    Act Density 0.921%

    No Known Activations