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

    Neuronpedia

    INDEX
    Explanations

    has have

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     geweest
    0.96
     been
    0.96
    been
    0.95
     Been
    0.94
     BEEN
    0.90
     varit
    0.87
    Been
    0.81
     gewesen
    0.79
     были
    0.74
     ollut
    0.73
    POSITIVE LOGITS
     largely
    0.77
     increasingly
    0.70
     steadily
    0.70
     Increasingly
    0.63
     certainly
    0.59
     progressively
    0.59
     점점
    0.59
     요즘
    0.55
     اکنون
    0.55
     désormais
    0.54
    Act Density 0.055%

    No Known Activations