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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Em
    -0.07
     Stamford
    -0.06
    Be
    -0.06
     packages
    -0.06
     гід
    -0.06
    spam
    -0.06
     Meet
    -0.06
    ors
    -0.06
    ٠
    -0.06
     gained
    -0.06
    POSITIVE LOGITS
     '{$
    0.07
     평당
    0.06
     Ald
    0.06
    $MESS
    0.06
    ाओ
    0.06
    τή
    0.06
     elig
    0.06
     금
    0.06
    ')">
    0.06
    公告
    0.06
    Act Density 0.015%

    No Known Activations