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

    Neuronpedia

    INDEX
    Explanations

    Movies and books

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     viable
    -0.08
    enci
    -0.08
     sedent
    -0.07
    .connections
    -0.07
     tomou
    -0.07
     occupant
    -0.07
     feas
    -0.07
     certifications
    -0.07
     लाई
    -0.07
     beacon
    -0.07
    POSITIVE LOGITS
     작품
    0.14
    作品
    0.13
     karya
    0.11
     masterpieces
    0.10
     masterpiece
    0.10
     premiered
    0.10
     épisodes
    0.10
    发表于
    0.10
     unpublished
    0.09
     《
    0.09
    Act Density 0.154%

    No Known Activations