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

    Neuronpedia

    INDEX
    Explanations

    daily plans and durations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     an
    0.72
    ל
    0.62
    ם
    0.52
    Ta
    0.48
        
    0.48
    )
    0.48
     a
    0.47
    2
    0.47
    1
    0.47
    ล
    0.46
    POSITIVE LOGITS
    h
    0.68
     работа
    0.53
    రోజు
    0.49
     giornata
    0.48
    ط
    0.46
    ер
    0.45
     päev
    0.44
     недели
    0.42
    f
    0.42
    ंत्री
    0.42
    Act Density 0.161%

    No Known Activations