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

    Neuronpedia

    INDEX
    Explanations

    provisions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     provisions
    -0.72
    Jeografia
    -0.68
     surely
    -0.63
     lesser
    -0.63
     Provisions
    -0.59
    lichkeiten
    -0.58
     وتسجيلات
    -0.57
    ftagPool
    -0.56
    vogel
    -0.55
     eventually
    -0.54
    POSITIVE LOGITS
    nodoc
    0.54
    subpackage
    0.54
     disponibilités
    0.52
     EconPapers
    0.52
    eraan
    0.48
     qualify
    0.48
    ArgsConstructor
    0.48
     esternos
    0.48
    prüche
    0.46
     Byzantium
    0.46
    Act Density 0.787%

    No Known Activations