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

    Neuronpedia

    INDEX
    Explanations

    definitions and terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lahir
    0.45
     dünyaya
    0.45
     nacido
    0.43
     setCount
    0.42
     geboren
    0.40
     consentement
    0.40
    crossed
    0.39
     élections
    0.39
     lancé
    0.38
     lanzado
    0.38
    POSITIVE LOGITS
     acidification
    0.44
     Definition
    0.41
     hyper
    0.41
     دیکھیں
    0.36
     terms
    0.35
     definition
    0.35
    Term
    0.35
     Term
    0.35
    詞
    0.35
    名词
    0.35
    Act Density 0.001%

    No Known Activations