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

    Neuronpedia

    INDEX
    Explanations

    noise

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Lemma
    -0.07
    ectors
    -0.07
    nte
    -0.06
     구글
    -0.06
     pymysql
    -0.06
    zipcode
    -0.06
     Bulgaria
    -0.06
    egr
    -0.06
     Malaysia
    -0.06
    urring
    -0.06
    POSITIVE LOGITS
     envy
    0.07
    factory
    0.07
     refund
    0.06
    Ren
    0.06
    	contentPane
    0.06
     LO
    0.06
     REST
    0.06
    591
    0.06
     AA
    0.06
    kit
    0.06
    Act Density 0.005%

    No Known Activations