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

    Neuronpedia

    INDEX
    Explanations

    descriptive text and items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Awards
    0.52
     Award
    0.46
     Given
    0.43
     nginx
    0.43
     Recycle
    0.43
     Inserting
    0.43
     vỏ
    0.43
     Requests
    0.43
     Recycling
    0.43
     Has
    0.42
    POSITIVE LOGITS
    詩
    0.54
    ableness
    0.53
    事で
    0.51
    ferencia
    0.48
     frequência
    0.48
    🎵
    0.48
    니
    0.47
    睦
    0.47
    そ
    0.46
    樂
    0.46
    Act Density 0.002%

    No Known Activations