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

    Neuronpedia

    INDEX
    Explanations

    Russian language texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .poi
    -0.09
     โล
    -0.09
    โล
    -0.09
    .include
    -0.08
    toe
    -0.08
    ounty
    -0.08
    illion
    -0.08
    Mods
    -0.08
    .caption
    -0.08
    -0.07
    POSITIVE LOGITS
    ność
    0.08
     atau
    0.07
    اپ
    0.07
     Ernst
    0.07
     detective
    0.07
     marketplace
    0.07
     مسب
    0.07
     rynku
    0.07
     Copp
    0.07
     Kari
    0.07
    Act Density 0.001%
    No Known Activations