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

    Neuronpedia

    INDEX
    Explanations

    benefits and perks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     delegado
    0.38
     PURCH
    0.38
    Dougall
    0.37
     Xuân
    0.37
    opters
    0.36
     EXPRESS
    0.36
    ICIAL
    0.36
    ໂດ
    0.36
     beginnen
    0.35
    ábado
    0.35
    POSITIVE LOGITS
     Assistance
    0.38
     perks
    0.38
     இந்ந
    0.38
    ्यु
    0.37
     Closed
    0.37
    イベント
    0.36
    Fuel
    0.36
    Closed
    0.36
     onsite
    0.35
     акций
    0.35
    Act Density 0.000%

    No Known Activations