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

    Neuronpedia

    INDEX
    Explanations

    nobility

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    防空
    -0.07
    気
    -0.07
    噙
    -0.07
    WC
    -0.07
    进修
    -0.07
    إش
    -0.07
    lemn
    -0.07
    >;
    -0.07
    Structured
    -0.07
    建设工程
    -0.06
    POSITIVE LOGITS
     former
    0.07
     buttonText
    0.07
     Kat
    0.07
     impairment
    0.07
    az
    0.07
    ap
    0.07
    ár
    0.07
     Cancel
    0.07
    ot
    0.07
     Amar
    0.07
    Act Density 0.005%

    No Known Activations