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

    Neuronpedia

    INDEX
    Explanations

    failed logon attempts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    兴
    0.41
     headroom
    0.39
    魇
    0.39
     Wherever
    0.36
     жер
    0.36
    ेयर
    0.35
     मोल
    0.35
     spire
    0.35
    Wherever
    0.34
     wherever
    0.34
    POSITIVE LOGITS
     breakfast
    1.09
    breakfast
    1.09
    Breakfast
    1.02
     Breakfast
    0.95
    早餐
    0.92
     breakfasts
    0.91
     desayuno
    0.87
     Frühstück
    0.86
     desay
    0.77
     suspected
    0.73
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.