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

    Neuronpedia

    INDEX
    Explanations

    drill file

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vudd
    0.51
     oars
    0.50
     aturan
    0.50
     italiano
    0.49
     pears
    0.47
    CHREIB
    0.47
     パーカー
    0.47
     sağlı
    0.46
     seçenek
    0.46
     চিৎ
    0.46
    POSITIVE LOGITS
    ression
    0.57
    test
    0.50
    formation
    0.49
    he
    0.46
    tech
    0.45
    1
    0.45
    え
    0.45
    ed
    0.44
    唯一
    0.44
    灰
    0.44
    Act Density 0.005%

    No Known Activations