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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     diode
    -0.09
     여러분
    -0.09
     NOS
    -0.08
     서비스를
    -0.08
     नाग
    -0.08
    (store
    -0.08
     आपने
    -0.07
     любой
    -0.07
     еш
    -0.07
     Versand
    -0.07
    POSITIVE LOGITS
    /he
    0.07
     attrib
    0.07
    .alibaba
    0.07
    ,row
    0.07
     gradu
    0.07
    :white
    0.07
     decay
    0.07
     divers
    0.07
     desal
    0.07
     homeland
    0.06
    Act Density 0.003%

    No Known Activations