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

    Neuronpedia

    INDEX
    Explanations

    the fact that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ে
    2.55
    ه
    2.33
    ς
    1.95
    AN
    1.89
     exons
    1.87
    ƒ
    1.79
     Behold
    1.77
    さすが
    1.77
     hafa
    1.74
    𝗔
    1.74
    POSITIVE LOGITS
    ually
    2.55
    상
    2.55
    stücke
    2.47
     saill
    2.44
    적인
    2.41
    ları
    2.34
    ل
    2.30
    st
    2.19
    لل
    2.19
    larda
    2.17
    Act Density 0.017%

    No Known Activations