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

    Neuronpedia

    INDEX
    Explanations

    press

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ac
    -0.08
     advertising
    -0.08
     ac
    -0.08
     мебели
    -0.07
     directed
    -0.07
     dose
    -0.07
     promoc
    -0.07
     incr
    -0.07
    advert
    -0.07
     materials
    -0.07
    POSITIVE LOGITS
    лес
    0.08
     Recently
    0.08
     noexcept
    0.08
    ioned
    0.08
     Jeffrey
    0.08
    verlening
    0.08
     pretrained
    0.08
    िव
    0.08
    ionato
    0.08
    ेदारी
    0.08
    Act Density 0.002%

    No Known Activations