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

    Neuronpedia

    INDEX
    Explanations

    instructions and tasks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     payable
    0.41
     as
    0.37
     leased
    0.35
     acetylcholine
    0.34
     caud
    0.34
     analogous
    0.32
     atop
    0.32
     contrived
    0.32
     dint
    0.32
     array
    0.32
    POSITIVE LOGITS
    Игра
    0.35
    欧美
    0.35
     Люди
    0.35
     পোকামাকড়
    0.35
    Câu
    0.34
    Για
    0.34
    Β
    0.34
     Работа
    0.34
    You
    0.33
    Α
    0.33
    Act Density 0.006%

    No Known Activations