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

    Neuronpedia

    INDEX
    Explanations

    Acronyms and file paths

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    resents
    -0.09
    ्रत
    -0.09
    REFERRED
    -0.09
    urity
    -0.09
    оряд
    -0.08
    redict
    -0.08
    ровер
    -0.08
    rint
    -0.08
    olicy
    -0.08
    refix
    -0.08
    POSITIVE LOGITS
     PA
    0.10
     Paw
    0.10
    -p
    0.10
    P
    0.10
     P
    0.10
     p
    0.09
     Pav
    0.09
    p
    0.09
     Pack
    0.09
     Pierre
    0.09
    Act Density 4.494%

    No Known Activations