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

    Neuronpedia

    INDEX
    Explanations

    prioritize data, preferred, cozy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    дель
    0.46
    糖
    0.46
     штат
    0.45
    ˗
    0.45
    кре
    0.42
     Resin
    0.41
    τυ
    0.41
    ^{-}$
    0.41
    surgical
    0.40
     resins
    0.40
    POSITIVE LOGITS
     때
    0.47
     يؤ
    0.46
     unor
    0.46
     ascend
    0.46
     날
    0.44
     പോലും
    0.43
     작업을
    0.43
     அங்க
    0.43
     넓
    0.43
     Geb
    0.42
    Act Density 0.008%

    No Known Activations