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

    Neuronpedia

    INDEX
    Explanations

    achievements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    enskap
    -0.64
    ism
    -0.63
    ization
    -0.63
    neath
    -0.60
    ess
    -0.59
    ist
    -0.59
    verwijspagina
    -0.59
    ette
    -0.57
    ostante
    -0.57
    lace
    -0.57
    POSITIVE LOGITS
    s
    0.93
    Personendaten
    0.64
    i
    0.54
    Seeder
    0.54
    senti
    0.53
    a
    0.53
    庁
    0.52
    ی
    0.52
     LoggerFactory
    0.51
    Migrations
    0.50
    Act Density 0.281%

    No Known Activations