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

    Neuronpedia

    INDEX
    Explanations

    the importance of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ouchement
    0.72
     dichiarato
    0.72
    >,
    0.71
     непосредственно
    0.70
    ੀਆਂ
    0.66
    oplevel
    0.66
    owany
    0.66
    FERRED
    0.65
     ishlab
    0.65
     adjudged
    0.65
    POSITIVE LOGITS
     importance
    4.18
    importance
    3.72
    Importance
    3.67
     Importance
    3.61
     importancia
    3.25
     importância
    3.24
    importanza
    3.15
     need
    2.74
     важно
    2.52
     اهمیت
    2.49
    Act Density 0.153%

    No Known Activations