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

    Neuronpedia

    INDEX
    Explanations

    recommends or is good

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sogenannte
    0.42
     paradigms
    0.41
     determinations
    0.40
    EntityFramework
    0.39
     catastrophic
    0.38
    妄
    0.38
     mesenchymal
    0.38
     framebuffer
    0.37
    とされる
    0.37
     termed
    0.37
    POSITIVE LOGITS
    おすすめです
    0.64
     also
    0.61
     также
    0.57
     👍
    0.57
     inoltre
    0.54
     recommande
    0.53
    👍
    0.53
     👌
    0.53
     лучше
    0.52
     മികച്ച
    0.51
    Act Density 0.049%

    No Known Activations