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

    Neuronpedia

    INDEX
    Explanations

    note and important information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     badly
    0.77
     until
    0.75
    वायरमेंट
    0.71
     Приступљено
    0.70
    galkan
    0.70
     зав
    0.69
     così
    0.69
     stared
    0.69
    วิ
    0.69
    Ended
    0.68
    POSITIVE LOGITS
     Note
    1.73
     note
    1.71
     important
    1.66
     importante
    1.62
    Note
    1.61
    note
    1.57
     Important
    1.55
    Important
    1.49
     notes
    1.45
    important
    1.39
    Act Density 0.413%

    No Known Activations