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

    Neuronpedia

    INDEX
    Explanations

    Pronouns for people

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     chính
    -0.07
    Numbers
    -0.07
     thief
    -0.06
     ele
    -0.06
    .serializer
    -0.06
    combo
    -0.06
     Aynı
    -0.06
     fis
    -0.06
    	fclose
    -0.06
    [][]
    -0.06
    POSITIVE LOGITS
     cause
    0.06
    向
    0.06
     relations
    0.06
     Imperial
    0.06
    _CAP
    0.06
    Za
    0.06
     Iowa
    0.06
     I
    0.06
    �
    0.06
    �
    0.06
    Act Density 0.065%

    No Known Activations