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

    Neuronpedia

    INDEX
    Explanations

    their

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ಅವನು
    1.33
     그는
    1.24
     yourself
    1.20
     Оно
    1.17
     оно
    1.11
    あなたが
    1.09
    あなたは
    1.07
     он
    1.06
    彼は
    1.06
     Он
    1.01
    POSITIVE LOGITS
     their
    7.30
    their
    6.76
    Their
    6.55
     Their
    6.38
     их
    6.34
    他们的
    6.13
     leurs
    6.01
     leur
    5.93
    他們的
    5.90
     їх
    5.88
    Act Density 1.876%

    No Known Activations