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

    Neuronpedia

    INDEX
    Explanations

    vie

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    はじめに
    -0.79
    IntoConstraints
    -0.79
     bezeichneter
    -0.75
    WaitGroup
    -0.73
    -0.73
    ьаж
    -0.71
    Искәрмәләр
    -0.71
    Personendaten
    -0.70
    minecraft
    -0.68
     nakalista
    -0.67
    POSITIVE LOGITS
    gibt
    0.54
     enfans
    0.53
     exécu
    0.49
    antiate
    0.49
    chiat
    0.48
     iNdEx
    0.47
    updated
    0.46
    ekwondo
    0.46
     darte
    0.45
     gefeiert
    0.45
    Act Density 0.108%

    No Known Activations