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

    Neuronpedia

    INDEX
    Explanations

    encryption

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _content
    -0.08
     cycle
    -0.07
     runners
    -0.07
    CADE
    -0.07
     seal
    -0.06
    _lists
    -0.06
     elbow
    -0.06
    (Note
    -0.06
    comes
    -0.06
     Purs
    -0.06
    POSITIVE LOGITS
     raspberry
    0.08
     özg
    0.06
     příro
    0.06
     яб
    0.06
     underwater
    0.06
     numpy
    0.06
     JAXBElement
    0.06
     osp
    0.06
     leggings
    0.06
    bro
    0.06
    Act Density 0.016%

    No Known Activations