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

    Neuronpedia

    INDEX
    Explanations

    default, long, numpy, non

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Pembroke
    0.30
     Durham
    0.29
     Donegal
    0.28
    这个
    0.28
     Clermont
    0.28
     Birmingham
    0.27
     SAL
    0.27
     CY
    0.27
     Sedona
    0.27
     Wesley
    0.27
    POSITIVE LOGITS
     tiež
    0.32
     마찬가지
    0.32
     kullanarak
    0.31
     izan
    0.30
    രാഷ്ട്ര
    0.30
     jeżeli
    0.30
     kecuali
    0.30
     തുടർ
    0.30
     ጣ
    0.29
     anecd
    0.29
    Act Density 0.199%

    No Known Activations