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

    Neuronpedia

    INDEX
    Explanations

    generated

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Autoritní
    -0.93
    Vidite
    -0.85
    contentLoaded
    -0.81
     autorytatywna
    -0.78
     AssemblyCulture
    -0.77
    Хьажоргаш
    -0.77
    WebElementEntity
    -0.73
    MessageTagHelper
    -0.72
     يتيمه
    -0.71
    KommentareTeilen
    -0.70
    POSITIVE LOGITS
    <bos>
    0.46
    enumii
    0.45
    ofern
    0.42
    ↵↵
    0.40
     request
    0.40
     kul
    0.40
    іга
    0.40
    Well
    0.38
     estimate
    0.38
     have
    0.38
    Act Density 0.053%

    No Known Activations