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

    Neuronpedia

    INDEX
    Explanations

    main or principal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     unwittingly
    0.68
    ITURE
    0.66
     unconsciously
    0.64
     vedno
    0.64
    াতার
    0.62
    ücks
    0.61
    めでとう
    0.61
     unnoticed
    0.61
    庻
    0.60
    ueux
    0.60
    POSITIVE LOGITS
     main
    4.95
    main
    4.19
    主要
    3.96
     principais
    3.91
    的主要
    3.90
     principali
    3.90
     मुख्य
    3.76
     principales
    3.71
     основных
    3.70
     principaux
    3.68
    Act Density 2.935%

    No Known Activations