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

    Neuronpedia

    INDEX
    Explanations

    currently

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     diesmal
    -0.08
    -0.08
     устройства
    -0.08
     повод
    -0.08
     lässt
    -0.08
     современные
    -0.07
     �
    -0.07
     производ
    -0.07
     Watson
    -0.07
     зр
    -0.07
    POSITIVE LOGITS
    स्थित
    0.09
    verde
    0.08
    യായി
    0.08
     exile
    0.08
     unanswered
    0.08
    看来
    0.08
     hairstyles
    0.08
    Nas
    0.07
    燃
    0.07
    为空
    0.07
    Act Density 0.025%
    No Known Activations