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

    Neuronpedia

    INDEX
    Explanations

    experiments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wikipagina
    -0.87
    Datuak
    -0.85
     Wikiseite
    -0.78
    WebVitals
    -0.74
     fidé
    -0.73
     للاسماء
    -0.72
     propOrder
    -0.71
    contentLoaded
    -0.71
     EconPapers
    -0.69
    Personendaten
    -0.68
    POSITIVE LOGITS
     on
    0.49
     
    0.48
    ’
    0.48
    <bos>
    0.47
    ↵↵
    0.46
     (
    0.42
     antibiotics
    0.41
    toxins
    0.40
     EDTA
    0.39
    toxin
    0.38
    Act Density 0.349%

    No Known Activations