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

    Neuronpedia

    INDEX
    Explanations

    introduces specific concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     หรือ
    0.62
     and
    0.61
    Но
    0.60
     (_
    0.58
     (\"
    0.57
     και
    0.57
              
    0.57
                              
    0.57
     },
    0.57
     или
    0.56
    POSITIVE LOGITS
    oretically
    0.96
    odore
    0.94
    jenigen
    0.76
     proverbial
    0.70
     biggest
    0.67
     scourge
    0.67
     highest
    0.67
     loudest
    0.66
     brightest
    0.66
     pinnacle
    0.66
    Act Density 0.151%

    No Known Activations