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
    寓
    -0.07
    有多么
    -0.07
     sez
    -0.07
     meds
    -0.07
    いず
    -0.06
     graf
    -0.06
    秕
    -0.06
    ackle
    -0.06
    ols
    -0.06
    alles
    -0.06
    POSITIVE LOGITS
    -call
    0.08
     MER
    0.07
    computed
    0.07
    癌症
    0.07
    强迫
    0.07
    初步
    0.07
     Mutual
    0.07
    cente
    0.06
    letion
    0.06
    حيا
    0.06
    Act Density 0.019%

    No Known Activations