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

    Neuronpedia

    INDEX
    Explanations

    */

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Plymouth
    -0.07
     Fiesta
    -0.07
    ainties
    -0.06
    �
    -0.06
    coni
    -0.06
     injections
    -0.06
     chơi
    -0.06
     Total
    -0.06
     daha
    -0.06
     leases
    -0.06
    POSITIVE LOGITS
    aed
    0.08
    不久前
    0.07
    你可以
    0.07
     modify
    0.07
    FILENAME
    0.07
    裁
    0.07
    .modified
    0.07
    rtype
    0.07
     müssen
    0.07
     resourceName
    0.06
    Act Density 0.007%

    No Known Activations