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

    Neuronpedia

    INDEX
    Explanations

    thoughts or urges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sthe
    1.82
    relief
    1.78
    الأ
    1.76
    uniform
    1.75
    acheteur
    1.75
    plural
    1.74
    restaurants
    1.70
    kaan
    1.70
    autista
    1.69
    rectangular
    1.68
    POSITIVE LOGITS
     理
    1.56
     respecting
    1.50
    理
    1.47
     ENTRY
    1.45
    行
    1.44
    爲
    1.42
    藉
    1.42
    洽
    1.41
    兴
    1.41
     Entering
    1.41
    Act Density 0.009%

    No Known Activations