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

    Neuronpedia

    INDEX
    Explanations

    Technical and academic texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     noveller
    -0.06
    (ad
    -0.06
     deut
    -0.06
    .pp
    -0.06
    ocre
    -0.06
    平
    -0.06
    相
    -0.06
     Blowjob
    -0.06
    -helper
    -0.06
     Arbeits
    -0.06
    POSITIVE LOGITS
    Catch
    0.07
     Senior
    0.06
     advent
    0.06
    Hum
    0.06
     signing
    0.06
    Commands
    0.06
     fastest
    0.06
     although
    0.06
     बड
    0.06
    显示
    0.06
    Act Density 0.001%

    No Known Activations