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

    Neuronpedia

    INDEX
    Explanations

    spending categories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nagyobb
    0.43
     уравнение
    0.43
     считать
    0.42
    Ссылки
    0.40
    Equations
    0.40
     எதிர
    0.39
     discus
    0.38
     Seorang
    0.38
    Linki
    0.38
    жная
    0.38
    POSITIVE LOGITS
    डेंट
    0.45
    URIS
    0.40
    MER
    0.40
     localize
    0.39
    ey
    0.39
    ony
    0.38
    HE
    0.38
     cancellation
    0.38
    agog
    0.38
    兇
    0.38
    Act Density 0.001%

    No Known Activations