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

    Neuronpedia

    INDEX
    Explanations

    computer parts

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Toni
    0.58
     Heg
    0.57
     Pellegr
    0.56
    Pearson
    0.56
     الو
    0.55
    าว
    0.55
     मूर्त
    0.54
     小物
    0.54
    EPS
    0.53
     गोपनीयता
    0.53
    POSITIVE LOGITS
    upgrade
    0.55
     Therm
    0.54
    рее
    0.54
    చు
    0.53
     therm
    0.53
     upgrading
    0.52
     RAID
    0.52
     upgrad
    0.52
     nanoscale
    0.52
     नान
    0.50
    Act Density 0.002%

    No Known Activations