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

    Neuronpedia

    INDEX
    Explanations

    HTML code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     accomplished
    -0.07
    istol
    -0.07
     Serif
    -0.07
     panc
    -0.07
    之所
    -0.07
     ransom
    -0.07
    zł
    -0.07
    Persons
    -0.06
    北大
    -0.06
    沁
    -0.06
    POSITIVE LOGITS
    arking
    0.08
     jquery
    0.08
    جار
    0.07
    曰
    0.07
    ":{"
    0.07
     заявил
    0.07
     Flyers
    0.07
    ивается
    0.07
    pping
    0.07
     которой
    0.07
    Act Density 0.126%

    No Known Activations