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

    Neuronpedia

    INDEX
    Explanations

    despite

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    MMdd
    -0.49
     Paglinawan
    -0.49
    chiha
    -0.49
     grâce
    -0.46
    izable
    -0.46
    $'
    -0.46
    yska
    -0.46
    itization
    -0.45
    :+:
    -0.43
     vorder
    -0.43
    POSITIVE LOGITS
     that
    0.96
     which
    0.77
    UnusedPrivate
    0.68
     having
    0.62
    ardless
    0.59
     fact
    0.57
     اینکه
    0.56
     lesquels
    0.55
     bahwa
    0.55
     them
    0.55
    Act Density 0.002%

    No Known Activations