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

    Neuronpedia

    INDEX
    Explanations

    general context or category

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     וכ
    2.14
    ться
    2.08
    یت
    1.88
    ación
    1.88
    িশালী
    1.87
    вая
    1.84
    ação
    1.77
    एस
    1.77
    િસ
    1.77
     padrão
    1.75
    POSITIVE LOGITS
    alities
    1.90
     plats
    1.77
    izability
    1.74
     blockers
    1.72
    isations
    1.68
    izable
    1.67
    naires
    1.64
    vieve
    1.63
    ב
    1.63
     ámbitos
    1.62
    Act Density 0.094%

    No Known Activations