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

    Neuronpedia

    INDEX
    Explanations

    confidential after and

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Assassin
    0.41
     সকাল
    0.39
     সন্ধ্যার
    0.39
     IconButton
    0.37
     বিকেল
    0.37
     Hours
    0.37
     kematian
    0.37
     शाम
    0.36
    営業時間
    0.36
     सुबह
    0.36
    POSITIVE LOGITS
     வகு
    0.40
     ロ
    0.36
    órmula
    0.36
     alatt
    0.34
     キャン
    0.34
    Rut
    0.34
     чет
    0.34
     الماض
    0.34
    Arq
    0.34
    ména
    0.34
    Act Density 0.054%

    No Known Activations