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

    Neuronpedia

    INDEX
    Explanations

    Camera, antenna, currency, dunes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ра
    0.97
    ing
    0.89
     élèves
    0.88
    .
    0.86
    ประโยชน์
    0.85
     ermög
    0.84
     listrik
    0.83
     mij
    0.82
     donnée
    0.82
     segí
    0.81
    POSITIVE LOGITS
    به
    0.91
    Jed
    0.90
    داً
    0.90
     및
    0.89
    और
    0.88
     and
    0.86
    Пер
    0.85
    ectomy
    0.85
     एवं
    0.85
    mena
    0.82
    Act Density 0.558%

    No Known Activations