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

    Neuronpedia

    INDEX
    Explanations

    can the, have the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Т
    0.38
    Б
    0.34
    Ч
    0.34
    Ц
    0.33
    РИ
    0.31
    К
    0.31
    يت
    0.30
    Ј
    0.30
    Он
    0.29
    И
    0.29
    POSITIVE LOGITS
    ä
    0.48
     müşter
    0.36
     një
    0.35
     satış
    0.35
     që
    0.35
     The
    0.34
    ın
    0.34
    นำ
    0.34
     sınıf
    0.34
     şi
    0.33
    Act Density 4.307%

    No Known Activations