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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     estudiantes
    -0.07
     Spor
    -0.07
     literature
    -0.07
     advertising
    -0.06
     leadership
    -0.06
     fans
    -0.06
    .ag
    -0.06
     Depart
    -0.06
     above
    -0.06
     Clone
    -0.06
    POSITIVE LOGITS
    @login
    0.06
    MX
    0.06
    /${
    0.06
     conexao
    0.06
    irst
    0.06
    fon
    0.06
     disadv
    0.06
    }{$
    0.06
    $tmp
    0.06
     �
    0.06
    Act Density 0.019%

    No Known Activations