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

    Neuronpedia

    INDEX
    Explanations

    sorting by category

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    每個
    0.49
     любом
    0.47
    任何
    0.42
    全て
    0.42
     divided
    0.41
    Divid
    0.41
    时代的
    0.41
     সর্বত্র
    0.40
     dividido
    0.39
    全ての
    0.39
    POSITIVE LOGITS
     categories
    0.66
     categorie
    0.55
     categorías
    0.55
     category
    0.52
     fairly
    0.52
     categorias
    0.51
     approaches
    0.50
     catégories
    0.48
     somewhat
    0.48
    categorie
    0.47
    Act Density 0.030%

    No Known Activations