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

    Neuronpedia

    INDEX
    Explanations

    Spanish/Portuguese words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ("----------------
    -0.07
     analogous
    -0.06
     tantal
    -0.06
     bfs
    -0.06
     chỉnh
    -0.06
     Confederate
    -0.06
     rig
    -0.06
     Menu
    -0.05
     sci
    -0.05
    BuildContext
    -0.05
    POSITIVE LOGITS
    ITA
    0.08
    Slides
    0.07
    ita
    0.07
     palavra
    0.07
     invaluable
    0.07
    َة
    0.06
     workplace
    0.06
    َد
    0.06
    inkel
    0.06
     responsible
    0.06
    Act Density 0.006%

    No Known Activations