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

    Neuronpedia

    INDEX
    Explanations

    Text fragments from technical documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     تضيفلها
    -0.85
    VIAF
    -0.78
    reportWebVitals
    -0.77
    SpringBootTest
    -0.75
    UIControlState
    -0.73
    elemField
    -0.73
     cherchés
    -0.71
    KURZBESCHREIBUNG
    -0.68
    parsedMessage
    -0.68
     ویکی‌پدیا
    -0.66
    POSITIVE LOGITS
     want
    0.63
     take
    0.60
     try
    0.57
     are
    0.57
     build
    0.56
     begin
    0.56
     freuen
    0.54
     use
    0.53
     start
    0.53
     get
    0.52
    Act Density 0.001%

    No Known Activations