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

    Neuronpedia

    INDEX
    Explanations

    gas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Marilyn
    -0.08
     emocional
    -0.08
    Reserva
    -0.07
     Naruto
    -0.07
    合彩
    -0.07
     Congrats
    -0.07
     Mika
    -0.07
     veto
    -0.07
    .Authorization
    -0.07
     독
    -0.07
    POSITIVE LOGITS
     medieval
    0.10
     historically
    0.09
     craftsmen
    0.09
    England
    0.09
    �
    0.09
     deeds
    0.08
     manor
    0.08
     kashe
    0.08
     degeneration
    0.08
     servant
    0.08
    Act Density 0.063%

    No Known Activations