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

    Neuronpedia

    INDEX
    Explanations

    technical/scientific texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     linkovi
    -0.65
     puffs
    -0.57
    archiviato
    -0.56
    ViewImports
    -0.55
     للمعارف
    -0.54
    teries
    -0.52
     disambiguazione
    -0.52
    ItemBackground
    -0.51
    Sucesor
    -0.51
    junto
    -0.50
    POSITIVE LOGITS
    (!__
    0.63
    </tfoot>
    0.56
    rozco
    0.53
     LeBlanc
    0.51
    __*/
    0.49
     SafeMath
    0.49
    assination
    0.48
    autorest
    0.47
    composer
    0.47
    getWriter
    0.47
    Act Density 0.002%

    No Known Activations