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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    </caption>
    -0.50
     AssemblyCulture
    -0.50
    initComponents
    -0.47
    :✨
    -0.47
     المعيارى
    -0.45
    uyer
    -0.45
    PreferredItem
    -0.45
    पया
    -0.44
     resided
    -0.44
    koliv
    -0.43
    POSITIVE LOGITS
     FetchType
    0.64
    Референце
    0.63
     مشين
    0.61
     everybody
    0.58
    vetrain
    0.57
     everyone
    0.56
     betweenstory
    0.54
     MyBatis
    0.54
     unknownFields
    0.53
     BoxFit
    0.53
    Act Density 0.003%

    No Known Activations