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

    Neuronpedia

    INDEX
    Explanations

    AMD Radeon RX

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     práce
    0.81
     funkce
    0.81
     arbeiten
    0.79
    вик
    0.79
     fonctionner
    0.77
     sounded
    0.77
     begonnen
    0.76
     funktionieren
    0.75
     vedit
    0.75
     visible
    0.75
    POSITIVE LOGITS
     Bad
    0.62
     bad
    0.61
    不妨
    0.58
    繰
    0.56
     ब्राउन
    0.56
    bad
    0.55
     را
    0.54
     comfortably
    0.53
     Bienvenido
    0.53
    PTION
    0.52
    Act Density 0.024%

    No Known Activations