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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     the
    -0.73
     his
    -0.58
     AppCompat
    -0.56
     their
    -0.54
     them
    -0.49
     Above
    -0.48
     BorderRadius
    -0.47
    ActivityCompat
    -0.47
    hacia
    -0.47
    MockMvc
    -0.46
    POSITIVE LOGITS
     disambiguazione
    1.01
    verwijspagina
    0.91
    <bos>
    0.73
    rungsseite
    0.72
     Савезне
    0.70
    зулта
    0.70
    NameInMap
    0.68
     Drapeau
    0.66
     Bourgoin
    0.63
     дописавши
    0.62
    Act Density 0.003%

    No Known Activations