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

    Neuronpedia

    INDEX
    Explanations

    historical accounts and sources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     разре
    0.42
     ARXIV
    0.42
    🎹
    0.41
     ఒ
    0.41
    再現
    0.41
    öffentlichung
    0.40
    વાનું
    0.40
    Exhibit
    0.40
     dSample
    0.40
     जिल्ह्यात
    0.39
    POSITIVE LOGITS
     historian
    0.93
     historians
    0.89
     histori
    0.88
     chronicles
    0.86
     Histories
    0.86
     histories
    0.84
     chronicle
    0.84
     chronic
    0.80
     Chronicles
    0.72
    Hist
    0.72
    Act Density 0.015%

    No Known Activations