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

    Neuronpedia

    INDEX
    Explanations

    specific nouns or concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     zákaz
    0.45
    ItemBackground
    0.43
     nouveaux
    0.42
     optar
    0.41
     novos
    0.40
     المنتج
    0.40
    ضيع
    0.39
    )));
    0.39
    顧客
    0.39
     nový
    0.39
    POSITIVE LOGITS
    หรือ
    0.52
     включает
    0.52
    NOT
    0.47
     kirj
    0.46
     अथवा
    0.45
    Т
    0.45
    気の
    0.45
     явля
    0.44
     extranj
    0.44
    CLUDES
    0.44
    Act Density 0.002%

    No Known Activations