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

    Neuronpedia

    INDEX
    Explanations

    Complex sentence structure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    好看
    -0.07
    /wiki
    -0.06
    nEnter
    -0.06
    $GLOBALS
    -0.06
    [arg
    -0.06
    阑
    -0.06
     feared
    -0.06
    恫
    -0.06
    🤐
    -0.06
     paypal
    -0.06
    POSITIVE LOGITS
     atrav
    0.08
    饨
    0.07
     עבודה
    0.07
    مج
    0.06
     Дмитр
    0.06
     LOCAL
    0.06
     muted
    0.06
    ß
    0.06
    🕝
    0.06
    읔
    0.06
    Act Density 0.180%

    No Known Activations