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

    Neuronpedia

    INDEX
    Explanations

    alphabets and languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Analysis
    -0.07
    RDD
    -0.06
    �
    -0.06
     Rox
    -0.06
    prt
    -0.06
     lesen
    -0.06
    ,S
    -0.06
    (dict
    -0.06
     exhibits
    -0.06
     Celtics
    -0.06
    POSITIVE LOGITS
    ocommerce
    0.07
    dotenv
    0.06
    -ignore
    0.06
     lacks
    0.06
     AppModule
    0.06
     Animals
    0.06
    Writes
    0.06
    heel
    0.06
    學
    0.06
     carg
    0.06
    Act Density 0.006%

    No Known Activations