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

    Neuronpedia

    INDEX
    Explanations

    executing turns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Utama
    0.48
     Основ
    0.43
     utama
    0.43
    低
    0.42
     低
    0.42
    Low
    0.41
    Trước
    0.41
     Plow
    0.39
     इंटीग्रेशन
    0.38
    Sales
    0.38
    POSITIVE LOGITS
    intrusion
    0.41
     invaded
    0.39
    يرة
    0.39
     მაგ
    0.37
    itors
    0.36
    ího
    0.36
    ítico
    0.36
    ってしまう
    0.36
    äle
    0.36
     nick
    0.35
    Act Density 0.000%

    No Known Activations