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

    Neuronpedia

    INDEX
    Explanations

    Numerical measurements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     epit
    -0.08
    rsp
    -0.07
    RARY
    -0.07
    ства
    -0.06
     proprietary
    -0.06
     estate
    -0.06
     were
    -0.06
     Homo
    -0.06
     HIS
    -0.06
    utz
    -0.06
    POSITIVE LOGITS
    SECTION
    0.07
    ）。↵
    0.06
    _listen
    0.06
     ได
    0.06
     －
    0.06
     sinon
    0.06
     فت
    0.06
    :)];↵
    0.06
     :)↵
    0.06
     coloring
    0.06
    Act Density 0.044%

    No Known Activations