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

    Neuronpedia

    INDEX
    Explanations

    multilingual character representations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    on
    0.48
     là
    0.48
    ereal
    0.48
    ın
    0.47
    ite
    0.47
     как
    0.47
    ene
    0.46
    eti
    0.46
    ilable
    0.46
    ere
    0.45
    POSITIVE LOGITS
    બ
    0.52
    María
    0.51
    瑙
    0.50
    Literatura
    0.49
     griech
    0.49
    Ге
    0.48
    ྪ
    0.48
     materiál
    0.48
    杨
    0.46
    Fighting
    0.46
    Act Density 0.000%

    No Known Activations