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

    Neuronpedia

    INDEX
    Explanations

    fuels and heating oil

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     seiz
    0.42
     道
    0.42
    樟
    0.42
    aviation
    0.40
    道の
    0.40
    指向
    0.40
    クラ
    0.40
    航空
    0.40
    она
    0.40
    device
    0.38
    POSITIVE LOGITS
     bunker
    0.50
     Bunker
    0.49
     bunk
    0.46
     bunkers
    0.43
     peels
    0.42
    QB
    0.42
     dailySales
    0.41
     ash
    0.39
     peeled
    0.38
     ನೆಲ
    0.38
    Act Density 0.003%

    No Known Activations