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

    Neuronpedia

    INDEX
    Explanations

    process changes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     prepaid
    -0.07
     defend
    -0.07
    ISTR
    -0.07
    usal
    -0.06
    -la
    -0.06
    гля
    -0.06
     spar
    -0.06
    Whole
    -0.06
     yık
    -0.06
    睛
    -0.06
    POSITIVE LOGITS
     libertine
    0.06
    (OS
    0.06
     remnants
    0.06
    CMS
    0.06
    054
    0.06
    ******/↵↵
    0.06
    */
    0.06
    _since
    0.06
    pivot
    0.06
    digit
    0.05
    Act Density 0.011%

    No Known Activations