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

    Neuronpedia

    INDEX
    Explanations

    que

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oram
    -0.07
    -tip
    -0.06
    ibly
    -0.06
    _story
    -0.06
     uncovered
    -0.06
     کوت
    -0.06
    cheiden
    -0.06
     titanium
    -0.06
    -sama
    -0.06
    cete
    -0.06
    POSITIVE LOGITS
    emek
    0.07
     เด
    0.07
    [...,
    0.06
    ้าอ
    0.06
    template
    0.06
    xs
    0.06
     Ames
    0.06
     Obrázky
    0.06
     celé
    0.06
     المو
    0.06
    Act Density 0.012%

    No Known Activations