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

    Neuronpedia

    INDEX
    Explanations

    things can get better

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     generate
    0.69
     gauge
    0.67
    িলারা
    0.67
    बोल
    0.66
     지급
    0.65
     correlate
    0.65
     perform
    0.65
    引起
    0.65
     correlating
    0.64
     peril
    0.64
    POSITIVE LOGITS
    美好
    0.86
    turn
    0.84
     felicidade
    0.84
     turned
    0.82
     любов
    0.82
     güzel
    0.80
     pans
    0.80
    anesi
    0.80
     sprawy
    0.79
     pan
    0.78
    Act Density 0.016%

    No Known Activations