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

    Neuronpedia

    INDEX
    Explanations

    Math symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     સલ
    -0.09
    ieken
    -0.09
     izvo
    -0.08
     zee
    -0.08
     arty
    -0.08
     faiz
    -0.08
     renseignements
    -0.08
     ұсыны
    -0.08
     વિગતો
    -0.08
     תוכלו
    -0.08
    POSITIVE LOGITS
     versão
    0.08
     Version
    0.08
     versions
    0.08
     shifted
    0.08
     version
    0.08
     versión
    0.08
    Version
    0.07
     Moj
    0.07
     shifting
    0.07
     Versions
    0.07
    Act Density 0.025%

    No Known Activations