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

    Neuronpedia

    INDEX
    Explanations

    AI techniques

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SXml
    0.57
     Ру
    0.51
     Диа
    0.48
     Поли
    0.48
     ఒకటి
    0.47
     Ци
    0.47
     Современ
    0.47
    peri
    0.46
     Север
    0.46
     Пів
    0.46
    POSITIVE LOGITS
     tanggal
    0.46
     enzimas
    0.46
     arrives
    0.45
     muncul
    0.44
    GA
    0.43
     crunchy
    0.43
     fechas
    0.43
     BTU
    0.42
    히
    0.42
     giorno
    0.41
    Act Density 0.000%

    No Known Activations