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

    Neuronpedia

    INDEX
    Explanations

    old and ancient things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nasce
    0.63
    ด
    0.59
    éné
    0.57
     běž
    0.56
    入荷
    0.54
    er
    0.54
     cleanly
    0.53
     garantizar
    0.52
     finished
    0.52
     É
    0.52
    POSITIVE LOGITS
     old
    1.01
     পুরনো
    0.96
     पुराने
    0.95
     viejo
    0.94
    old
    0.91
     vieux
    0.91
     পুরোনো
    0.91
    Old
    0.88
    舊
    0.86
     OLD
    0.84
    Act Density 0.186%

    No Known Activations