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

    Neuronpedia

    INDEX
    Explanations

    predicting maintenance and anomalies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autonomous
    0.91
    Autonomous
    0.87
     profundamente
    0.83
     Pun
    0.82
    haan
    0.82
     நான
    0.81
     Autonomous
    0.80
     terceiro
    0.80
     tortured
    0.79
     result
    0.78
    POSITIVE LOGITS
     Date
    1.47
    date
    1.40
     date
    1.37
     DATE
    1.35
     expires
    1.34
    Date
    1.31
     даты
    1.31
     expire
    1.30
    dates
    1.30
     dates
    1.27
    Act Density 0.540%

    No Known Activations