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

    Neuronpedia

    INDEX
    Explanations

    mentions of the flu, reactors, and science and medicine

    oai_token-act-pair · gemini-2.0-flash

    flu

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     refer
    -0.63
     real
    -0.61
     (“
    -0.61
     von
    -0.59
    ’,
    -0.56
     rent
    -0.54
     (‘
    -0.53
     med
    -0.53
     in
    -0.52
     sin
    -0.51
    POSITIVE LOGITS
     trasparente
    1.10
    :✨
    1.09
     vermelha
    1.02
     eletrônico
    1.02
     polvere
    1.02
     dourada
    0.99
     isolado
    0.97
     Cæsar
    0.96
     romántica
    0.95
     anún
    0.94
    Act Density 2.664%

    No Known Activations