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

    Neuronpedia

    INDEX
    Explanations

    predictive maintenance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     コー
    0.43
    0.42
     kivy
    0.42
     irritate
    0.41
     ffm
    0.40
     консо
    0.40
    0.40
     hợp
    0.39
     अंशु
    0.39
    0.39
    POSITIVE LOGITS
    保养
    0.71
    Maintenance
    0.64
     maintenance
    0.64
    メンテナンス
    0.59
     mantenimiento
    0.59
     upkeep
    0.57
    maintenance
    0.57
     Maintenance
    0.55
     manutenção
    0.53
     பராம
    0.52
    Act Density 0.006%

    No Known Activations