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

    Neuronpedia

    INDEX
    Explanations

    UI buttons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Holmes
    0.40
    COc
    0.38
    聯合
    0.38
    沬
    0.37
    쳐
    0.36
    Parliament
    0.36
    දිය
    0.36
    脊
    0.36
    myItemType
    0.35
     fellowships
    0.35
    POSITIVE LOGITS
     button
    3.95
     buttons
    3.64
    ボタン
    3.52
     Button
    3.50
    按钮
    3.47
    button
    3.42
    Button
    3.38
     버튼
    3.34
     बटन
    3.30
     Buttons
    3.22
    Act Density 0.111%

    No Known Activations