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

    Neuronpedia

    INDEX
    Explanations

    HTML name attribute assignment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    图标
    0.52
     icon
    0.42
     emblem
    0.41
    アイコン
    0.40
     damp
    0.40
    ässig
    0.39
     favors
    0.39
     integral
    0.38
    Fav
    0.38
     shaken
    0.38
    POSITIVE LOGITS
    keywords
    0.83
     keywords
    0.72
    Keywords
    0.72
     Keywords
    0.68
    author
    0.65
    キーワード
    0.59
    viewport
    0.56
     author
    0.56
    KEYWORDS
    0.53
    Author
    0.52
    Act Density 0.003%

    No Known Activations