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

    Neuronpedia

    INDEX
    Explanations

    equated or defined

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ֜
    0.44
    чә
    0.39
    amsu
    0.38
    ouss
    0.38
     considerably
    0.37
    Qt
    0.37
    方向
    0.37
     지도
    0.37
     endeavour
    0.37
     सचिवा
    0.37
    POSITIVE LOGITS
     অনন্য
    0.42
     Davie
    0.42
     Charger
    0.41
     Departure
    0.41
     ชอบ
    0.41
     Unique
    0.41
     deregulation
    0.41
     Heavenly
    0.40
     Chargers
    0.40
    leriyle
    0.40
    Act Density 0.001%

    No Known Activations