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

    Neuronpedia

    INDEX
    Explanations

    online booking sites and policies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Dining
    0.54
     dining
    0.47
    Entertainment
    0.45
    dining
    0.44
    ズニー
    0.43
     যশ
    0.43
    餐厅
    0.42
    骋
    0.42
     thrill
    0.42
    PARTY
    0.42
    POSITIVE LOGITS
     €
    0.48
     dialogues
    0.47
     Albanian
    0.47
     (€
    0.44
     sg
    0.43
     hered
    0.43
     euros
    0.42
     WhatsApp
    0.42
     Armenian
    0.42
     relat
    0.42
    Act Density 0.013%

    No Known Activations