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

    Neuronpedia

    INDEX
    Explanations

    picked

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bel
    -0.07
    .Controllers
    -0.07
    ùy
    -0.06
     lông
    -0.06
    Wifi
    -0.06
    发展
    -0.06
     geographic
    -0.06
     централь
    -0.06
     Chocolate
    -0.06
     annotations
    -0.06
    POSITIVE LOGITS
     dictionaryWith
    0.07
     dựng
    0.07
     与
    0.06
     pois
    0.06
     dentro
    0.06
    (p
    0.06
    -pin
    0.06
     prevents
    0.06
    [mid
    0.06
     maintenant
    0.06
    Act Density 0.001%

    No Known Activations