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

    Neuronpedia

    INDEX
    Explanations

    articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     limité
    -0.08
     beperkt
    -0.08
     mediated
    -0.08
     limitée
    -0.08
    -mediated
    -0.07
    larning
    -0.07
     areia
    -0.07
    poč
    -0.07
    ייח
    -0.07
     limitado
    -0.07
    POSITIVE LOGITS
     lungs
    0.08
     Africans
    0.08
     Cann
    0.08
     Danger
    0.08
     развед
    0.07
     envision
    0.07
     Contr
    0.07
     consegu
    0.07
     получится
    0.07
     ungef
    0.07
    Act Density 0.003%

    No Known Activations