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

    Neuronpedia

    INDEX
    Explanations

    clauses following that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     by
    0.25
    ها
    0.23
     (
    0.23
    es
    0.22
    사
    0.22
     for
    0.22
    ים
    0.21
     ,
    0.21
     ("
    0.21
     ซึ่ง
    0.20
    POSITIVE LOGITS
    ऊंगी
    0.18
    स्तों
    0.18
    liegt
    0.18
     REALLY
    0.18
     existed
    0.18
     opravdu
    0.17
     specialize
    0.17
     ressemble
    0.17
     profissionais
    0.17
    ῎
    0.17
    Act Density 0.278%

    No Known Activations