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

    Neuronpedia

    INDEX
    Explanations

    between consecutive

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     еще
    0.96
     äuß
    0.93
     ещё
    0.91
     главным
    0.88
    úrate
    0.87
     außerhalb
    0.87
    racción
    0.86
     кислоты
    0.86
     самым
    0.86
     изобра
    0.83
    POSITIVE LOGITS
    در
    1.02
     immunocom
    0.88
    צ
    0.88
     dementia
    0.81
     reproductive
    0.81
    द
    0.80
     obesity
    0.79
     immunity
    0.79
     mainland
    0.79
     pensions
    0.79
    Act Density 0.000%

    No Known Activations