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

    Neuronpedia

    INDEX
    Explanations

    commas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ,
    -0.53
    Aholisi
    -0.51
     مرئيه
    -0.51
    例句
    -0.50
     ModelExpression
    -0.46
    StreetMap
    -0.45
     iconTwitter
    -0.45
    DoubleQuotes
    -0.44
     transi
    -0.43
     ब्रेकडाउन
    -0.43
    POSITIVE LOGITS
     “
    0.68
     épaules
    0.62
     poussière
    0.62
    ági
    0.60
     löyty
    0.59
     complètes
    0.59
     fumée
    0.57
     föruts
    0.57
    |
    0.57
     renseignements
    0.57
    Act Density 0.001%

    No Known Activations