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

    Neuronpedia

    INDEX
    Explanations

    News articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bacteria
    -0.07
     decade
    -0.07
    .car
    -0.07
     né
    -0.07
     moins
    -0.07
    quared
    -0.06
     manoe
    -0.06
     SOAP
    -0.06
     convent
    -0.06
    .request
    -0.06
    POSITIVE LOGITS
    .ExecuteScalar
    0.07
     pornstar
    0.06
     derecho
    0.06
    	comment
    0.06
    вает
    0.06
    [column
    0.06
    wig
    0.06
    tring
    0.06
     Beng
    0.06
    TERS
    0.06
    Act Density 0.002%

    No Known Activations