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

    Neuronpedia

    INDEX
    Explanations

    Sure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -death
    -0.08
    深
    -0.06
    古
    -0.06
     останні
    -0.06
     BDS
    -0.06
     раніше
    -0.06
    [first
    -0.06
    folio
    -0.06
    18
    -0.06
    06
    -0.06
    POSITIVE LOGITS
    ~↵
    0.07
    -↵
    0.07
     Criminal
    0.07
     há
    0.07
    .CSS
    0.06
     gal
    0.06
     invented
    0.06
     all
    0.06
     ESP
    0.06
     @@↵
    0.06
    Act Density 0.017%

    No Known Activations