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

    Neuronpedia

    INDEX
    Explanations

    law

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Περ
    -0.07
     yerleştir
    -0.07
    nim
    -0.07
     humili
    -0.07
    el
    -0.07
    -fiction
    -0.07
    itial
    -0.07
     выдел
    -0.07
     Fiesta
    -0.07
    eli
    -0.06
    POSITIVE LOGITS
     law
    0.15
     Law
    0.13
    Law
    0.12
    law
    0.11
     Laws
    0.11
     LAW
    0.11
     laws
    0.10
    法
    0.09
    laws
    0.09
    AW
    0.09
    Act Density 0.029%

    No Known Activations