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

    Neuronpedia

    INDEX
    Explanations

    8

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    amo
    -0.06
     mammals
    -0.06
    езда
    -0.06
    try
    -0.06
    ento
    -0.06
    ullo
    -0.06
     Jared
    -0.06
     salts
    -0.06
    erte
    -0.06
    ience
    -0.06
    POSITIVE LOGITS
     negocio
    0.07
     adipiscing
    0.06
    DonaldTrump
    0.06
     objectType
    0.06
    kın
    0.06
     ancest
    0.06
     Disconnect
    0.06
     использов
    0.06
    imilar
    0.06
    dataTable
    0.06
    Act Density 0.002%

    No Known Activations