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

    Neuronpedia

    INDEX
    Explanations

    welcome greetings introductions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bâtiment
    0.53
     izinsuku
    0.43
     упо
    0.42
     bâtiments
    0.42
     escrever
    0.41
     solidar
    0.41
     prédio
    0.41
     unclaimed
    0.40
     edifici
    0.40
     botón
    0.40
    POSITIVE LOGITS
     welcome
    0.88
     welcomed
    0.88
    欢迎
    0.88
    welcome
    0.79
    Welcome
    0.76
     Welcome
    0.76
     welcoming
    0.73
    歡迎
    0.71
    accueil
    0.71
     bienvenida
    0.63
    Act Density 0.005%

    No Known Activations