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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Delete
    -0.07
    へ
    -0.07
     فيها
    -0.06
     COMPUTER
    -0.06
    同
    -0.06
     Education
    -0.06
     ---
    -0.06
    记
    -0.06
    �
    -0.05
    .Accept
    -0.05
    POSITIVE LOGITS
    نتاج
    0.07
     quot
    0.07
    $res
    0.07
     Dost
    0.07
    [{
    0.07
    whelming
    0.06
    ğit
    0.06
    reh
    0.06
    nic
    0.06
    db
    0.06
    Act Density 0.006%

    No Known Activations