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

    Neuronpedia

    INDEX
    Explanations

    service or RFC

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     সমস্ত
    0.43
    il
    0.43
    碴
    0.43
     Polskiej
    0.42
    .?
    0.42
     Rest
    0.42
     Necklace
    0.42
    ak
    0.41
    scala
    0.41
     Investigative
    0.41
    POSITIVE LOGITS
     ارائه
    0.54
    IDF
    0.53
     اولیه
    0.50
    𒃲
    0.49
     খ
    0.46
    дис
    0.46
     وړاند
    0.46
     внутреннего
    0.46
     estimating
    0.45
     biosynthetic
    0.44
    Act Density 0.000%

    No Known Activations