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

    Neuronpedia

    INDEX
    Explanations

    code and lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    তাদের
    0.43
     konserv
    0.42
    颢
    0.42
     welcoming
    0.42
    द
    0.42
    ুদের
    0.42
    രിച്ചത്
    0.40
    Есть
    0.39
     theirs
    0.39
     equivoc
    0.39
    POSITIVE LOGITS
    []{
    0.45
     компакт
    0.43
     Optical
    0.41
    bing
    0.40
    .,
    0.40
     Compact
    0.40
    writelines
    0.40
     manzanas
    0.40
    -[
    0.39
     थीटा
    0.39
    Act Density 0.050%

    No Known Activations