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

    Neuronpedia

    INDEX
    Explanations

    childhood names and scenarios

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     חיי
    0.47
     Букмекер
    0.46
    健身
    0.44
    atsby
    0.43
     инвести
    0.42
    誡
    0.42
     strtotime
    0.42
    ベーション
    0.42
     року
    0.42
    ೇವೆ
    0.42
    POSITIVE LOGITS
     어린이
    0.83
    🧒
    0.79
     کودک
    0.78
     preschool
    0.78
    👧
    0.77
     niño
    0.75
     children
    0.74
     menino
    0.74
     बच्ची
    0.72
     الأطفال
    0.72
    Act Density 0.136%

    No Known Activations