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

    Neuronpedia

    INDEX
    Explanations

    offers help based on data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rites
    0.52
     crimen
    0.47
    નુ
    0.47
     spasms
    0.47
     parses
    0.46
     deuter
    0.45
     curses
    0.44
     なさい
    0.44
     Benjamin
    0.44
     carreg
    0.44
    POSITIVE LOGITS
    Warranty
    0.44
    Вы
    0.42
    begin
    0.41
    This
    0.41
    Guarantee
    0.41
    Aluminum
    0.41
    windows
    0.40
    lease
    0.39
     চিকিৎস
    0.39
    contract
    0.39
    Act Density 0.001%

    No Known Activations