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

    Neuronpedia

    INDEX
    Explanations

    single letters and abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    هن
    0.55
    бурга
    0.47
    ᔕ
    0.47
    Ფ
    0.45
    ంబేద్
    0.45
    ERICK
    0.44
    هام
    0.44
    اش
    0.43
    បន្ថ
    0.43
    جان
    0.43
    POSITIVE LOGITS
    you
    0.59
     c
    0.57
     p
    0.56
     you
    0.55
    0.52
    js
    0.47
    that
    0.46
     l
    0.45
     g
    0.45
    if
    0.44
    Act Density 0.116%

    No Known Activations