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

    Neuronpedia

    INDEX
    Explanations

    JavaScript

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    @[+][
    -0.59
    Personendaten
    -0.52
     xenia
    -0.50
     Boxer
    -0.49
     rosse
    -0.48
     prieten
    -0.47
     ambientale
    -0.47
     depic
    -0.47
    ียว
    -0.47
     dourado
    -0.47
    POSITIVE LOGITS
    المكان
    0.65
    Geplaatst
    0.60
    WebServlet
    0.60
    AllowUser
    0.60
    </caption>
    0.59
    RetentionPolicy
    0.59
    ITECT
    0.57
     оригіналу
    0.56
    pective
    0.56
    ilibrium
    0.55
    Act Density 0.141%

    No Known Activations