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

    Neuronpedia

    INDEX
    Explanations

    besides, including, exceptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     enfoque
    0.34
     জনপ্রিয়
    0.34
     caveat
    0.34
     concept
    0.33
     개념
    0.33
    нє
    0.33
     najwy
    0.32
     НЕ
    0.32
     vrai
    0.32
     safest
    0.32
    POSITIVE LOGITS
     除了
    0.61
    除了
    0.60
     包括
    0.59
    包括
    0.58
     помимо
    0.57
     besides
    0.55
     además
    0.55
     além
    0.54
    besides
    0.54
     Besides
    0.54
    Act Density 0.008%

    No Known Activations