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

    Neuronpedia

    INDEX
    Explanations

    words start with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    atured
    0.89
    身高
    0.87
    ozems
    0.80
    哥
    0.79
    交
    0.76
    jml
    0.75
    joined
    0.75
     মাপ
    0.74
    放
    0.74
    omét
    0.74
    POSITIVE LOGITS
     portal
    1.20
     brochure
    1.17
    (".");
    1.11
     folder
    1.11
     Portal
    1.11
     QFile
    1.09
     despite
    1.09
    คาเดมี
    1.09
     webpage
    1.09
     voucher
    1.08
    Act Density 0.234%

    No Known Activations