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

    Neuronpedia

    INDEX
    Explanations

    royal titles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Comun
    -0.56
     privada
    -0.50
     personali
    -0.49
     truth
    -0.47
    StrictEqual
    -0.47
    égalité
    -0.46
     disclosure
    -0.46
    caption
    -0.46
     Batalla
    -0.45
     personage
    -0.45
    POSITIVE LOGITS
     للاسماء
    0.87
     BoxFit
    0.76
    thâu
    0.75
     صوتيه
    0.72
    httphttps
    0.70
     ویکی‌پدیای
    0.66
     /\.(
    0.64
    SharedDtor
    0.64
     Waray
    0.63
    twimg
    0.63
    Act Density 0.005%

    No Known Activations