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

    Neuronpedia

    INDEX
    Explanations

    decisive wins or victories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fleks
    0.43
    راج
    0.41
    柔軟
    0.39
     flexible
    0.38
     superfici
    0.38
    灵活
    0.38
     flexibilidad
    0.38
    柔软
    0.37
    神経
    0.37
     agnostic
    0.37
    POSITIVE LOGITS
     landslide
    1.01
     shutout
    0.93
     margin
    0.89
     overwhelming
    0.85
     resounding
    0.83
     overwhelmingly
    0.81
     blowout
    0.80
     побе
    0.79
     victory
    0.78
     victoire
    0.77
    Act Density 0.010%

    No Known Activations