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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     estarán
    -0.09
     previamente
    -0.08
     estás
    -0.08
    html
    -0.08
     nachdem
    -0.08
     newly
    -0.08
     нельзя
    -0.08
     estará
    -0.07
     recién
    -0.07
    jlwm
    -0.07
    POSITIVE LOGITS
     Monsanto
    0.09
     neoliberal
    0.08
     democrat
    0.08
     globalization
    0.07
     multinational
    0.07
    議
    0.07
     mondial
    0.07
     dismant
    0.07
     vulgar
    0.07
     interessant
    0.07
    Act Density 0.088%

    No Known Activations