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

    Neuronpedia

    INDEX
    Explanations

    earlier or previously

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Y
    0.70
    '
    0.70
    ส่ง
    0.69
     credo
    0.69
     Athena
    0.68
     ERISA
    0.68
     тих
    0.66
     θε
    0.65
     ETL
    0.64
    ด้วย
    0.62
    POSITIVE LOGITS
    ين
    1.16
    ير
    1.06
    á
    1.02
    Earlier
    0.91
    يد
    0.89
    í
    0.89
    ip
    0.88
    ী
    0.88
    ı
    0.82
    ă
    0.81
    Act Density 0.002%

    No Known Activations