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

    Neuronpedia

    INDEX
    Explanations

    retaining rights and reservations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     payoffs
    0.38
    ဴ
    0.37
    जना
    0.37
     পেলাম
    0.37
    予算
    0.36
    빱
    0.35
     Rit
    0.34
     কুল
    0.33
     trav
    0.33
     salari
    0.33
    POSITIVE LOGITS
     reserved
    1.64
     reserve
    1.55
     reserves
    1.54
    reserve
    1.44
    reserved
    1.44
     reserving
    1.38
    Reserved
    1.38
     Reserved
    1.35
     reserv
    1.31
     rezerv
    1.29
    Act Density 0.004%

    No Known Activations