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

    Neuronpedia

    INDEX
    Explanations

    Norwegian, Danish, German endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    glightbox
    0.44
    带来
    0.41
    帶來
    0.41
    UGHT
    0.40
    離島
    0.39
    rolls
    0.38
    bringing
    0.38
    iemann
    0.37
     bringing
    0.37
     wheelchairs
    0.37
    POSITIVE LOGITS
    ede
    0.56
    tede
    0.50
    EDE
    0.47
    ayet
    0.45
    ning
    0.44
    metik
    0.43
    tet
    0.42
    udet
    0.42
     Tet
    0.42
    itet
    0.41
    Act Density 0.001%

    No Known Activations