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

    Neuronpedia

    INDEX
    Explanations

    example

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    กล
    -0.07
     هزار
    -0.06
     investigation
    -0.06
     typingsSlinky
    -0.06
     Collect
    -0.06
    Cách
    -0.06
    _%
    -0.06
    ηρε
    -0.06
    singular
    -0.06
     güc
    -0.06
    POSITIVE LOGITS
     Name
    0.07
    ',
↵
    0.07
     Flyers
    0.07
    cop
    0.06
    	tr
    0.06
     '))↵
    0.06
    dropdown
    0.06
    ~↵
    0.06
    の大
    0.06
    領
    0.06
    Act Density 0.013%

    No Known Activations